@lavralabs/lavra · Nerlo

@lavralabs/lavra

Version: v0.7.7
By: Roberto Mello
License: MIT
Last scan: Scanned Sep 3, 2026, 3:09 PM UTC

Claude Skill

Scan Haltedcomposite

Compound engineering with persistent memory and multi-agent workflows based on beads for Claude Code, OpenCode, Gemini CLI, and Cortex Code

Claude Skills are markdown + scripts loaded into Claude Code; scanned with the same pipeline.

Source:: github.com/roberto-mello/lavra
Version:: 0.7.7
License:: MIT
Author:: Roberto Mello
Provenance:: Found by crawling (provenance, not a security rating)

We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.

19 critical findings reported by cisco-skill-scanner, agent-audit-kit. The composite score alone does not reflect this — read the per-scanner reports below.

Install

Claude Skills install to a single target, no runtime picker.

nerlo install -- @lavralabs/lavra

Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.

cp -r -- @lavralabs/lavra ~/.claude/skills/

Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.

How scores work Full audit report

Per-scanner reports

7 scanners

Your view:

6 of 11 scanners examined this package. The rest do not apply to it — language, ecosystem and packaging decide which analyzers can say anything, and a scanner that cannot examine an artifact reports nothing rather than passing it.

Scanners that examined this package (6)

agentshield
v1.4.0
Caution66
- 52High
- 6Med
- 3Low
61 findings · 1.2s

AI review of these findings

Findings in files this artifact installs stand as reported; a model re-read the rest and said which ones it believes are false positives. This is a second opinion published beside the evidence, not a correction to it: the per-scanner reports above are unchanged, every dismissed finding is still listed there at its original severity, and the score and the Flagged badge are computed from those raw severities alone. Nothing below moved them.

Upheld as real: 201
Dismissed as false positives: 29
Not reviewed: 0

Out of 230 findings across every scanner that examined this package. None of the 19 findings rated critical by their scanner were dismissed.

Why those were dismissed

Two keys had to turn. The model had to name a reason from a fixed list of six, and a deterministic check of ours — over which files this artifact actually installs — had to independently agree. Anything it could not corroborate is in “not reviewed” above, at full severity.

21 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: PIPELINE_TAINT_FLOW, opt.nerlo-rules.nerlo-install-pipe-to-shell, AAK-STATE-PRIVACY-002 and 6 more · Files: /repo/site/src/content/docs/AUTONOMOUS_EXECUTION.md, /repo/site/src/content/docs/SKILL.md, site/src/content/docs/privacy.md and 10 more · reported by cisco-skill-scanner, nerlo-install-instruction, agent-audit-kit
6 Agent instruction file — The match is in a file that instructs an AI coding agent — a CLAUDE.md or similar. It is documentation of intent, and our own check confirmed it is not part of what gets installed.
Rules: agents-claude-md-autorun-3101, agents-comment-injection-5621, AAK-AGENT-005 · Files: CLAUDE.md, AGENTS.md · reported by agentshield, agent-audit-kit
2 CI or editor configuration — The match is in build, CI or editor configuration, confirmed by our own check to be outside the installed artifact.
Rules: AAK-GHA-IMMUTABLE-001 · Files: .github/workflows/deploy-site.yml, .github/workflows/test-installation.yml · reported by agent-audit-kit

In installed code — never dismissed

These findings are in files this artifact installs and are not placeholder values. No false-positive basis can be corroborated for such a finding, so this review never dismisses one; they were not sent to the model and stand at their scanner's severity.

46 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/lavra/skills/brainstorming/SKILL.md, /repo/plugins/lavra/skills/lavra-work-multi/SKILL.md, /repo/plugins/lavra/skills/agent-browser/SKILL.md and 43 more · reported by cisco-skill-scanner
18 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/.beads/SKILL.md, /repo/.claude/rules/SKILL.md and 15 more · reported by cisco-skill-scanner
8 FILE_MAGIC_MISMATCH
Files: /repo/plugins/lavra/skills/optional/dhh-rails-style/references/frontend.md, /repo/plugins/lavra/skills/create-agent-skills/templates/simple-skill.md · reported by cisco-skill-scanner
8 HIDDEN_DATA_FILE
Files: /repo/.beads/dolt-config.log, /repo/.beads/README.md, /repo/.beads/issues.jsonl and 5 more · reported by cisco-skill-scanner
8 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/.claude/rules/hooks-system.md, /repo/install.sh, /repo/plugins/lavra/commands/lavra-work-ralph.md and 4 more

Upheld — the review declined to dismiss these

The model could have called any of these a false positive and did not.

3 SQL_INJECTION_STRING_FORMAT
Files: /repo/scripts/sqlite-to-jsonl.py · reported by cisco-skill-scanner

What the review concluded

Critical risks: shell execution, script injection, and SQL injection.

The artifact contains multiple critical findings related to shell execution via command injection in JavaScript files like `/repo/bin/install.js` and `/repo/bin/plan-export.js`, and through installer scripts. Script injection vulnerabilities are present in `/repo/bin/plan-view.js`, potentially allowing arbitrary code execution. SQL injection vulnerabilities are identified in `/repo/scripts/sqlite-to-jsonl.py`, which could lead to unauthorized data access or manipulation. Additionally, a remote code execution hook is present in `.claude/hooks/memory-sanitize.sh`.

Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.

What to look at

AAK-HOOK-RCE-001 · .claude/hooks/memory-sanitize.sh · critical · reported by agent-audit-kit
AAK-MCP-001 · plugins/lavra/.mcp.json · critical · reported by agent-audit-kit
AAK-SKILL-001 · plugins/lavra/skills/agent-browser/SKILL.md · critical · reported by agent-audit-kit
COMMAND_INJECTION_JS_CHILD_PROCESS · /repo/bin/install.js · critical · reported by cisco-skill-scanner
COMMAND_INJECTION_JS_CHILD_PROCESS · /repo/bin/install.js · critical · reported by cisco-skill-scanner
COMMAND_INJECTION_JS_CHILD_PROCESS · /repo/bin/plan-export.js · critical · reported by cisco-skill-scanner
COMMAND_INJECTION_JS_CHILD_PROCESS · · critical · reported by cisco-skill-scanner

Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.

Scan history

2 scans on record. Every scan's full results are retained immutably for 24 months.

Completed	Composite	Change	Scanners	Status
Sep 3, 2026	Scan Halted	—	agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·!: incompletenerlo-multi-source ·n/a: not applicable	rejected
Aug 4, 2026	Scan Halted	—	agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source ·n/a: not applicable	rejected

Per-scanner history:

AI review of these findings

Upheld as real: 201
Dismissed as false positives: 29
Not reviewed: 0

Out of 230 findings across every scanner that examined this package. None of the 19 findings rated critical by their scanner were dismissed.

Why those were dismissed

21 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: PIPELINE_TAINT_FLOW, opt.nerlo-rules.nerlo-install-pipe-to-shell, AAK-STATE-PRIVACY-002 and 6 more · Files: /repo/site/src/content/docs/AUTONOMOUS_EXECUTION.md, /repo/site/src/content/docs/SKILL.md, site/src/content/docs/privacy.md and 10 more · reported by cisco-skill-scanner, nerlo-install-instruction, agent-audit-kit
6 Agent instruction file — The match is in a file that instructs an AI coding agent — a CLAUDE.md or similar. It is documentation of intent, and our own check confirmed it is not part of what gets installed.
Rules: agents-claude-md-autorun-3101, agents-comment-injection-5621, AAK-AGENT-005 · Files: CLAUDE.md, AGENTS.md · reported by agentshield, agent-audit-kit
2 CI or editor configuration — The match is in build, CI or editor configuration, confirmed by our own check to be outside the installed artifact.
Rules: AAK-GHA-IMMUTABLE-001 · Files: .github/workflows/deploy-site.yml, .github/workflows/test-installation.yml · reported by agent-audit-kit

In installed code — never dismissed

46 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/lavra/skills/brainstorming/SKILL.md, /repo/plugins/lavra/skills/lavra-work-multi/SKILL.md, /repo/plugins/lavra/skills/agent-browser/SKILL.md and 43 more · reported by cisco-skill-scanner
18 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/.beads/SKILL.md, /repo/.claude/rules/SKILL.md and 15 more · reported by cisco-skill-scanner
8 FILE_MAGIC_MISMATCH
Files: /repo/plugins/lavra/skills/optional/dhh-rails-style/references/frontend.md, /repo/plugins/lavra/skills/create-agent-skills/templates/simple-skill.md · reported by cisco-skill-scanner
8 HIDDEN_DATA_FILE
Files: /repo/.beads/dolt-config.log, /repo/.beads/README.md, /repo/.beads/issues.jsonl and 5 more · reported by cisco-skill-scanner
8 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/.claude/rules/hooks-system.md, /repo/install.sh, /repo/plugins/lavra/commands/lavra-work-ralph.md and 4 more

Upheld — the review declined to dismiss these

The model could have called any of these a false positive and did not.

3 SQL_INJECTION_STRING_FORMAT
Files: /repo/scripts/sqlite-to-jsonl.py · reported by cisco-skill-scanner

What the review concluded

Critical risks: shell execution, script injection, and SQL injection.

Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.

What to look at

AAK-HOOK-RCE-001 · .claude/hooks/memory-sanitize.sh · critical · reported by agent-audit-kit
AAK-MCP-001 · plugins/lavra/.mcp.json · critical · reported by agent-audit-kit
AAK-SKILL-001 · plugins/lavra/skills/agent-browser/SKILL.md · critical · reported by agent-audit-kit
COMMAND_INJECTION_JS_CHILD_PROCESS · /repo/bin/install.js · critical · reported by cisco-skill-scanner
COMMAND_INJECTION_JS_CHILD_PROCESS · /repo/bin/install.js · critical · reported by cisco-skill-scanner
COMMAND_INJECTION_JS_CHILD_PROCESS · /repo/bin/plan-export.js · critical · reported by cisco-skill-scanner
COMMAND_INJECTION_JS_CHILD_PROCESS · · critical · reported by cisco-skill-scanner

Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.

@lavralabs/lavra

Install

Per-scanner reports

Scanners that examined this package (6)

agentshield

cisco-skill-scanner

agent-audit-kit

nerlo-skill-scanner (behavioral)

nerlo-skill-scanner (install-doc)

capslock

Scanners that did not run on this package (5)

nerlo-multi-source

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Upheld — the review declined to dismiss these

What the review concluded

What to look at

Scan history

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Upheld — the review declined to dismiss these

What the review concluded

What to look at

Install

Per-scanner reports

Scanners that examined this package (6)

agentshield

cisco-skill-scanner

agent-audit-kit

nerlo-skill-scanner (behavioral)

nerlo-skill-scanner (install-doc)

capslock

Scanners that did not run on this package (5)

nerlo-multi-source

Composite scoreOne view among many — the per-scanner reports above are primaryScan Halted

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Upheld — the review declined to dismiss these

What the review concluded

What to look at

Scan history

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Upheld — the review declined to dismiss these

What the review concluded

What to look at