Loading the registry…
Portable Endor Labs workflow agents for AI coding hosts
Claude Skills are markdown + scripts loaded into Claude Code; scanned with the same pipeline.
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.
github_release: https://github.com/endorlabs/endor-labs-agent-kit, 0 findings
Claude Skills install to a single target, no runtime picker.
nerlo install -- endor-labs-agent-kit
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- endor-labs-agent-kit ~/.claude/skills/
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
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.
v2.0.11
335 findings · 53.5s
v0.3.74
30 findings · 73.9s
v0.1.0
2 findings · 13.9s
v0.1.0
0 findings · 14.0s
v0.1.0
0 findings · 19.2s
v2.3.8
0 findings · 0.2s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.2s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
v0.71.0
No dependency manifest or lockfile was found in this artifact. What each scanner covers
0 findings · 1.3s
v0.71.0
No container image was published for this artifact. What each scanner covers
0 findings · 0.0s
vv1.6.0
No Go modules were found in this artifact. What each scanner covers
0 findings · 0.1s
2 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Sep 3, 2026 | Flagged76 | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: completetrivy ·n/a: not applicableosv-scanner: completetrivy_image ·n/a: not applicablegovulncheck ·n/a: not applicable | completed |
| Aug 11, 2026 | Flagged70 | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicabletrivy ·n/a: not applicableosv-scanner: completetrivy_image ·n/a: not applicablegovulncheck ·n/a: not applicable | completed |
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 367 findings across every scanner that examined this package.
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.
6 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE · Files: /repo/docs/SKILL.md, /repo/.github/ISSUE_TEMPLATE/SKILL.md, /repo/.github/PULL_REQUEST_TEMPLATE/SKILL.md · reported by cisco-skill-scanner
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: MANIFEST_INVALID_NAME · Files: /repo/.github/PULL_REQUEST_TEMPLATE/SKILL.md, /repo/.github/ISSUE_TEMPLATE/SKILL.md · reported by cisco-skill-scanner
1 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-IPI-WILD-CORPUS-001 · Files: portable/configuration-automation/agent.md · 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.
144 MANIFEST_MISSING_LICENSE
Files: /repo/codex/remediation-planning/SKILL.md, /repo/codex/findings-browser/SKILL.md, /repo/codex/cicd-posture/SKILL.md and 141 more · reported by cisco-skill-scanner
84 FILE_MAGIC_MISMATCH
Files: /repo/plugins/codex-directory/endor-labs-agent-kit/skills/remediation-planning/agents/openai.yaml, /repo/plugins/codex-directory/endor-labs-agent-kit/skills/findings-browser/agents/openai.yaml, /repo/plugins/codex-directory/endor-labs-agent-kit/skills/cicd-posture/agents/openai.yaml and 31 more · reported by cisco-skill-scanner
54 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/cursor-sdk/SKILL.md, /repo/plugins/SKILL.md and 51 more · reported by cisco-skill-scanner
19 YARA_prompt_injection_unicode_steganography
Files: /repo/assets/logo.png, /repo/plugins/antigravity/endor-labs-agent-kit/assets/logo.png, /repo/plugins/claude/ai-plugins/assets/logo.png and 5 more · reported by cisco-skill-scanner
10 HIDDEN_DATA_FILE
Files:
Artifact contains multiple high-severity findings, including credential exposure and network egress.
The artifact includes exposed credentials in `keys/catalog-signing-public-key.pem` and exhibits network egress capabilities from a secret. Multiple instances of prompt injection concealment are present in various `SKILL.md` files, and asset prompt injection is noted in `evals/cases.yaml`. Additionally, several files related to marketplace and agent configurations contain high-severity findings.
Concern level assessed by the review: High. 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.
7 AAK-MARKETPLACE-001
Files: .cursor-plugin/marketplace.json, .claude-plugin/marketplace.json, plugins/codex/.agents/plugins/marketplace.json and 2 more · reported by agent-audit-kit
6 AAK-IPI-WILD-CORPUS-001
Files: codex/configuration-automation/SKILL.md, claude-code/configuration-automation/configuration-automation.md, source/agents/configuration-automation/instructions.md and 3 more · reported by agent-audit-kit
5 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/scripts/generate_endor_api_registry.py, /repo/src/endor_agent_kit/endor_context.py · reported by cisco-skill-scanner
4 ASSET_PROMPT_INJECTION
Files: /repo/source/agents/findings-browser/evals/cases.yaml, /repo/source/agents/malware-responder/evals/cases.yaml · reported by cisco-skill-scanner
4 PROMPT_INJECTION_CONCEALMENT
Files: /repo/codex/vulnerability-explainer/SKILL.md, /repo/gemini/vulnerability-explainer/SKILL.md, /repo/claude-code/vulnerability-explainer/SKILL.md and 1 more · reported by cisco-skill-scanner
3 AAK-MCP-007
Files: .mcp.json · reported by agent-audit-kit
3 AAK-SUPPLY-001
Files: .mcp.json · reported by agent-audit-kit
2 AAK-AGENT-SHARED-RES-AUTHZ-001
Files: catalog.json, manifest.json · reported by agent-audit-kit
2 AAK-MCP-ATTEST-001
Files: .mcp.json, plugins/codex/endor-labs-agent-kit/.mcp.json · reported by agent-audit-kit
2 EXCESSIVE_FILE_COUNT
Files: /repo/plugins/., /repo/. · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/cursor-sdk/run_cursor_agent.py · reported by nerlo-behavioral
1 AAK-MCP-005
Files: .mcp.json · reported by agent-audit-kit
1 AAK-MCP-006
Files: plugins/codex/endor-labs-agent-kit/.mcp.json · reported by agent-audit-kit
1 AAK-OAUTH-008
Files: claude-managed-agents/configuration-automation/agent.yaml · reported by agent-audit-kit
1 AAK-SECRET-005
Files: keys/catalog-signing-public-key.pem · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-TASKS-003
Files: src/endor_agent_kit/knowledge_pack.py · reported by agent-audit-kit
1 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/repo/CHANGELOG.md · reported by cisco-skill-scanner
Showing 25 of 29; the rest are in the per-scanner reports above.