Loading the registry…
Institutional memory for AI coding agents — capture decisions, rejected alternatives, and rationale across sessions
The publisher performed an authenticated act of publication — proving control of a namespace in the official MCP registry, or appearing in a first-party catalogue an operator curates. That establishes WHO published it. It is not a security finding, and attested artifacts carry Flagged verdicts too.
52 critical findings reported by cisco-skill-scanner, agent-audit-kit, 42 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
github: https://github.com/adelinamart/robrain, 667 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- robrain-monorepo
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
5 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.
v1.4.0
0 findings · 0.5s
v2.0.11
190 findings · 16.1s
v0.3.26
47 findings · 10.4s
v0.1.0
20 findings · 129.7s
v0.1.0
0 findings · 129.7s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image, nerlo-multi-source.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 7, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicable | rejected |
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.
Out of 257 findings across every scanner that examined this package. 10 of 52 findings rated critical by their scanner were among the dismissals.
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.
27 Test or fixture file — The match is in a test or fixture. Our own check confirmed the file is not part of what gets installed.
Rules: AAK-SECRET-003, SECRET_CONNECTION_STRING, AAK-TAINT-003 and 5 more · Files: packages/shared/src/redact.test.ts, /repo/packages/cli/src/commands/synth.test.ts, /repo/packages/shared/src/load-env.test.ts and 7 more · reported by agent-audit-kit, cisco-skill-scanner
11 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: FIND_EXEC_PATTERN, AAK-HEALTHCARE-AI-005, SOCIAL_ENG_VAGUE_DESCRIPTION and 1 more · Files: /repo/docs/SKILL.md, /repo/docs/troubleshooting.md, docs/release.md and 3 more · reported by cisco-skill-scanner, agent-audit-kit
9 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: AAK-AGENT-001, AAK-AGENT-005, TOOL_ABUSE_UNDECLARED_NETWORK · Files: AGENTS.md, /repo/repo/AGENTS.md · reported by agent-audit-kit, cisco-skill-scanner
7 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/publish-perception-image.yml, .github/workflows/ci.yml · reported by agent-audit-kit
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.
84 DATA_EXFIL_JS_NETWORK
Files: /repo/packages/cli/scripts/verify-release-artifacts.mjs, /repo/packages/cli/src/commands/check.ts, /repo/packages/cli/src/commands/doctor.ts and 17 more · reported by cisco-skill-scanner
34 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/packages/cli/scripts/verify-publish-tarball.mjs, /repo/packages/cli/scripts/verify-release-artifacts.mjs, /repo/packages/cli/src/commands/explain.ts and 7 more · reported by cisco-skill-scanner
18 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/packages/cli/scripts/verify-release-artifacts.mjs, /repo/packages/cli/src/commands/doctor.ts, /repo/packages/cli/src/lib/auth.ts and 6 more · reported by nerlo-behavioral
11 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/packages/vetobench/SKILL.md, /repo/packages/cli/SKILL.md and 8 more · reported by cisco-skill-scanner
11 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/packages/vetobench/SKILL.md, /repo/packages/cli/SKILL.md and 8 more
Critical command injection and credential harvesting risks identified.
The artifact contains multiple critical command injection vulnerabilities, primarily in CLI-related files, which could allow shell execution. It also exhibits critical credential harvesting capabilities and high-severity secret exfiltration over the network. These findings indicate significant risks related to system compromise and sensitive data exposure.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.
9 AAK-SECRET-004
Files: _next/static/chunks/03~yq9q893hmn.js, _next/static/chunks/0k86kt9uztsum.js, _next/static/chunks/06md4fclc9.he.js and 1 more · reported by agent-audit-kit
8 LOW_ANALYZABILITY
Files: /repo/plugins/claude-code, /repo/packages/eval, /repo/packages/cli and 5 more · reported by cisco-skill-scanner
5 YARA_credential_harvesting_generic
Files: /repo/packages/vetobench/results/frontier-none-baselines/openai-gpt-5-5-robrain-run-2.json, /repo/packages/vetobench/results/e2e-validation.json · reported by cisco-skill-scanner
4 AAK-LEGAL-002
Files: packages/synthesis/package.json, packages/perception-self-hosted/package.json, packages/vetobench/package.json and 1 more · reported by agent-audit-kit
3 PYCACHE_FILES_DETECTED
Files: /repo/integrations/hermes/__pycache__, /repo/integrations/hermes/robrain/__pycache__ · reported by cisco-skill-scanner
2 AAK-HEALTHCARE-AI-004
Files: packages/vetobench/results/frontier-none-baselines/openai-gpt-5-5-robrain-run-1.json, packages/vetobench/results/frontier-none-baselines/anthropic-claude-opus-4-8-robrain-run-2.json · reported by agent-audit-kit
2 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/packages/cli/src/lib/project.ts, /repo/packages/shared/src/llm.ts · reported by nerlo-behavioral
2 YARA_prompt_injection_generic
Files: /repo/packages/shared/src/trust.ts · reported by cisco-skill-scanner
1 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
1 AAK-MCP-018
Files: packages/sensing-mcp/src/server.ts · reported by agent-audit-kit
1 AAK-STATE-PRIVACY-001
Files: privacy.html · reported by agent-audit-kit
1 AAK-STATE-PRIVACY-002
Files: privacy.html · reported by agent-audit-kit
1 AAK-STATE-PRIVACY-003
Files: privacy.html · reported by agent-audit-kit
1 COMMAND_INJECTION_JS_FUNCTION_CONSTRUCTOR
Files: /repo/_next/static/chunks/03~yq9q893hmn.js · reported by cisco-skill-scanner
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 HIDDEN_DATA_FILE
Files: /repo/.nojekyll · reported by cisco-skill-scanner
1 MANIFEST_INVALID_NAME
Files: /repo/packages/vetobench/results/muse-spark-1.1-series/SKILL.md · reported by cisco-skill-scanner
1 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/integrations/hermes/robrain/repo/integrations/hermes/robrain/README.md · reported by cisco-skill-scanner
Showing 25 of 70; the rest are in the per-scanner reports above.