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.
90 critical findings reported by cisco-skill-scanner, agent-audit-kit, 87 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
Claude Skills install to a single target, no runtime picker.
nerlo install -- mantis-bot
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- mantis-bot ~/.claude/skills/
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 · 0.6s
v2.0.11
422 findings · 34.5s
v0.3.74
186 findings · 29.9s
v0.1.0
15 findings · 25.2s
v0.1.0
17 findings · 25.3s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 1.9s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 21, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source ·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 640 findings across every scanner that examined this package. 3 of 90 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.
26 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-MCP-001, AAK-MCP-ATTEST-001, YARA_prompt_injection_unicode_steganography and 4 more · Files: plugins/cowork-plugin-management/skills/cowork-plugin-customizer/examples/customized-mcp.json, /repo/docs/mantisbot-intro.png, /repo/docs/SKILL.md and 6 more · reported by agent-audit-kit, cisco-skill-scanner
5 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/release.yml · reported by agent-audit-kit
5 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-004, SECRET_PASSWORD_VAR · Files: src/auth/__tests__/jwt.test.ts, /repo/src/auth/__tests__/password.test.ts · reported by agent-audit-kit, cisco-skill-scanner
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.
143 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/productivity/skills/memory-management/SKILL.md, /repo/plugins/productivity/skills/task-management/SKILL.md, /repo/plugins/feishu-advanced/skills/feishu-bitable/SKILL.md and 140 more · reported by cisco-skill-scanner
68 AAK-MCP-001
Files: plugins/productivity/.mcp.json, plugins/sales/.mcp.json, plugins/product-management/.mcp.json and 6 more · reported by agent-audit-kit
68 AAK-MCP-ATTEST-001
Files: plugins/productivity/.mcp.json, plugins/sales/.mcp.json, plugins/product-management/.mcp.json and 6 more · reported by agent-audit-kit
64 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/skills/pptx/scripts/svg-utils.js, /repo/skills/email/scripts/imap.js, /repo/skills/email/scripts/smtp.js and 21 more · reported by cisco-skill-scanner
46 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/plugins/bio-research/skills/nextflow-development/scripts/utils/ncbi_utils.py, /repo/plugins/bio-research/skills/nextflow-development/scripts/check_environment.py, /repo/skills/openai-image-gen/scripts/gen.py
Critical command injection and data exfiltration risks identified.
The artifact contains critical command injection vulnerabilities, including potential remote code execution via SQL in `plugins/bio-research/skills/nextflow-development/scripts/utils/ncbi_utils.py` and through JavaScript child processes. It also exhibits capabilities for data exfiltration via file system access and network egress, with secrets potentially exposed to network connections. Additionally, the artifact can dynamically execute code and install system packages.
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.
41 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/data/agent-profiles/default/SKILL.md, /repo/data/agent-profiles/developer/SKILL.md and 38 more · reported by cisco-skill-scanner
35 DATA_EXFIL_JS_NETWORK
Files: /repo/skills/email/scripts/imap.js, /repo/src/agents/tools/feishu/oauth.ts, /repo/src/channels/http-ws/http-server.ts and 13 more · reported by cisco-skill-scanner
13 TOOL_ABUSE_SYSTEM_PACKAGE_INSTALL
Files: /repo/skills/ocr/scripts/ocr_pdf.py, /repo/install.sh · reported by cisco-skill-scanner
10 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/scripts/kill-port.cjs, /repo/scripts/postinstall.cjs, /repo/src/agents/skills/github-installer.ts and 2 more · reported by cisco-skill-scanner
9 HIDDEN_DATA_FILE
Files: /repo/plugins/legal/法律技能文档集_中文版.docx!/_rels/.rels, /repo/skills/self-improving-agent/.clawhub/origin.json, /repo/skills/self-improving-agent/.learnings/FEATURE_REQUESTS.md and 2 more · reported by cisco-skill-scanner
8 AAK-SECRET-004
Files: src/env-isolation.ts, src/cli.ts, src/memory/full-text-search-engine.ts and 4 more · reported by agent-audit-kit
8 LOW_ANALYZABILITY
Files: /repo/skills/email, /repo/web-ui/src/components, /repo/skills/self-improving-agent/hooks/openclaw and 5 more · reported by cisco-skill-scanner
8 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/src/agents/tools/feishu/oauth.ts, /repo/src/channels/http-ws/http-server.ts, /repo/src/channels/wecom/client.ts and 2 more · reported by nerlo-behavioral
7 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/README.md, /repo/install.sh, /repo/plugins/bio-research/skills/nextflow-development/SKILL.md and 2 more · reported by nerlo-install-instruction
7 PIPELINE_TAINT_FLOW
Files: /repo/plugins/bio-research/skills/nextflow-development/references/SKILL.md, /repo/plugins/bio-research/skills/nextflow-development/references/installation.md, /repo/install.sh and 2 more · reported by cisco-skill-scanner
6 AAK-HEALTHCARE-AI-004
Files: plugins/marketing/skills/brand-voice/SKILL.md, plugins/customer-support/skills/response-drafting/SKILL.md, plugins/customer-support/skills/ticket-triage/SKILL.md and 3 more · reported by agent-audit-kit
6 opt.nerlo-rules.nerlo-install-fetch-raw-then-run
Files: /repo/README.md, /repo/install.ps1, /repo/install.sh · reported by nerlo-install-instruction
5 UNANALYZABLE_BINARY
Files: /repo/skills/web-artifacts-builder/scripts/shadcn-components.tar.gz, /repo/plugins/legal/法律技能文档集_中文版.docx, /repo/skills/theme-factory/theme-showcase.pdf · reported by cisco-skill-scanner
4 SECRET_PASSWORD_VAR
Files: /repo/src/plugins/feishu-advanced/drive/doc-comments.ts, /repo/src/plugins/feishu-advanced/drive/doc-media.ts · reported by cisco-skill-scanner
3 AAK-OAUTH-007
Files: src/config/schema.ts, src/agents/tools/feishu/uat-store.ts, src/agents/tools/feishu/oauth.ts · reported by agent-audit-kit
3 AAK-SPLUNK-TOKLOG-001
Files: src/agents/openai-proxy.ts, src/channels/dingtalk/client.ts, src/channels/wecom/client.ts · reported by agent-audit-kit
3 ARCHIVE_FILE_DETECTED
Files: /repo/plugins/legal/法律技能文档集_中文版.docx, /repo/skills/web-artifacts-builder/scripts/shadcn-components.tar.gz · reported by cisco-skill-scanner
3 COMMAND_INJECTION_EVAL
Files: /repo/src/auth/db.ts, /repo/src/memory/node-sqlite-db.ts · reported by cisco-skill-scanner
3 opt.nerlo-rules.nerlo-dynamic-exec
Files: /repo/scripts/kill-port.cjs · reported by nerlo-behavioral
3 opt.nerlo-rules.nerlo-install-shell-inline-command
Files: /repo/install.sh · reported by nerlo-install-instruction
3 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/plugins/bio-research/skills/nextflow-development/repo/plugins/bio-research/skills/nextflow-development/SKILL.md, /repo/skills/openai-image-gen/repo/skills/openai-image-gen/SKILL.md, /repo/repo/BUILD_AND_RELEASE_GUIDE.md · reported by cisco-skill-scanner
2 AAK-ANTHROPIC-SDK-001
Files: src/plugins/mcp-client.ts, skills/mcp-builder/scripts/connections.py · reported by agent-audit-kit
2 AAK-DNS-REBIND-001
Files: src/plugins/mcp-client.ts, skills/mcp-builder/scripts/connections.py · reported by agent-audit-kit
2 AAK-LEGAL-002
Files: package.json, web-ui/package.json · reported by agent-audit-kit
2 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/src/channels/http-ws/http-server.ts · reported by nerlo-behavioral
2 YARA_code_execution_generic
Files: /repo/skills/docx/scripts/accept_changes.py · reported by cisco-skill-scanner
1 AAK-LLM-SQL-RCE-001
Files: plugins/bio-research/skills/nextflow-development/scripts/utils/ncbi_utils.py · reported by agent-audit-kit
1 AAK-MCP-004
Files: plugins/product-management/.mcp.json · reported by agent-audit-kit
1 AAK-MCP-SDK-CVE-2026-52869-001
Files: skills/mcp-builder/scripts/requirements.txt · reported by agent-audit-kit
1 AAK-MCP-SSRF-001
Files: src/plugins/feishu-advanced/tool-client.ts · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: package.json · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: package-lock.json · reported by agent-audit-kit
1 AAK-TAINT-001
Files: src/agents/claude-agent-runner.ts · reported by agent-audit-kit
1 COMPOUND_FETCH_EXECUTE
Files: /repo/install.sh · reported by cisco-skill-scanner
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 FILE_MAGIC_MISMATCH
Files: /repo/plugins/legal/法律技能文档集_中文版.docx · reported by cisco-skill-scanner
1 MANIFEST_INVALID_NAME
Files: /repo/skills/self-improving-agent/.learnings/SKILL.md · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/skills/webapp-testing/scripts/with_server.py · reported by nerlo-install-instruction
1 opt.nerlo-rules.nerlo-py-dynamic-exec
Files: /repo/skills/webapp-testing/scripts/with_server.py · reported by nerlo-behavioral
1 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/skills/openai-image-gen/scripts/gen.py · reported by nerlo-behavioral
1 SOCIAL_ENG_ANTHROPIC_IMPERSONATION
Files: /repo/skills/claude-api/SKILL.md · reported by cisco-skill-scanner
1 SOCIAL_ENG_MISLEADING_DESC
Files: /repo/plugins/bio-research/skills/nextflow-development/SKILL.md · reported by cisco-skill-scanner
1 YARA_coercive_injection_generic
Files: /repo/skills/claude-api/typescript/claude-api/SKILL.md · reported by cisco-skill-scanner
Showing 25 of 200; the rest are in the per-scanner reports above.