Loading the registry…
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.
1 critical finding reported by agent-audit-kit. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 2 sources and their verdicts differ. The worst is github (Flagged). Installing from a cleaner source does not mean the others are safe — check the source you actually install from.
github: https://github.com/hugoduncan/mcp-tasks, 84 findings
Claude Skills install to a single target, no runtime picker.
nerlo install -- 'hugoduncan/mcp-tasks (cli-usage)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'hugoduncan/mcp-tasks (cli-usage)' ~/.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
33 findings · 0.7s
v2.0.11
39 findings · 9.2s
v0.3.74
8 findings · 1.5s
v0.1.0
4 findings · 3.1s
v0.1.0
0 findings · 11.7s
v0.1.0
No source files this scanner can analyze were found in this artifact. What each scanner covers
0 findings · 3.1s
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.
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 ·n/a: not applicablenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: complete | 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 84 findings across every scanner that examined this package. None of the 1 finding rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 30 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.
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.
13 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-fetch-raw-then-run, opt.nerlo-rules.nerlo-install-pipe-to-shell and 2 more · Files: /repo/doc/install.md, /repo/doc/SKILL.md, /repo/doc/migration/SKILL.md and 2 more · reported by cisco-skill-scanner, nerlo-install-instruction
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/test.yml, .github/workflows/release.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.
9 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/mcp-tasks-cli/skills/cli-usage/SKILL.md, /repo/plugins/mcp-tasks-skill/skills/story-and-tasks/SKILL.md, /repo/SKILL.md and 6 more · reported by cisco-skill-scanner
8 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/plugins/mcp-tasks-cli/skills/cli-usage/SKILL.md, /repo/plugins/mcp-tasks-skill/skills/story-and-tasks/SKILL.md, /repo/SKILL.md and 5 more · reported by cisco-skill-scanner
5 FILE_MAGIC_MISMATCH
Files: /repo/resources/prompts/infrastructure/story-parsing.md, /repo/resources/prompts/create-story-pr.md · reported by cisco-skill-scanner
3 HIDDEN_DATA_FILE
Files: /repo/.clj-kondo/config.edn, /repo/.cljstyle, /repo/.clj-kondo/hooks/mcp_tasks/main_test.clj · reported by cisco-skill-scanner
2 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
29 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: skills-missing-telemetry-commands/mcp-tasks-execute-story-child.md, skills-missing-governance-commands/update-readme.md, skills-missing-governance-commands/mcp-tasks-optimize-prompts.md and 26 more · Files: commands/mcp-tasks-execute-story-child.md, commands/update-readme.md, commands/mcp-tasks-optimize-prompts.md and 12 more · reported by agentshield
1 The model did not answer for these findings.
Rules: skills-missing-governance-commands/mcp-tasks-execute-task.md · Files: commands/mcp-tasks-execute-task.md · reported by agentshield
Artifact contains critical security risks and shell execution instructions.
The artifact includes a critical finding related to a Marketplace Control Plane configuration in 'plugins/mcp-tasks-skill/.mcp.json'. It also contains high-severity instructions in 'README.md' that suggest piping content directly to a shell and fetching raw content for execution, which can lead to arbitrary shell execution. Additionally, there are high-severity issues with Marketplace configuration in '.claude-plugin/marketplace.json'.
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.
Files: /repo/README.md, /repo/SKILL.md · reported by cisco-skill-scanner
1 AAK-MCP-002
Files: plugins/mcp-tasks-skill/.mcp.json · reported by agent-audit-kit
1 AAK-MCP-006
Files: plugins/mcp-tasks-skill/.mcp.json · reported by agent-audit-kit
1 AAK-MCP-ATTEST-001
Files: plugins/mcp-tasks-skill/.mcp.json · reported by agent-audit-kit
1 AAK-SEC-MD-001
Files: SECURITY.md · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 hooks-no-pretooluse
Files: settings.json · reported by agentshield
1 hooks-no-stop-hooks
Files: settings.json · reported by agentshield
1 opt.nerlo-rules.nerlo-install-fetch-raw-then-run
Files: /repo/README.md · reported by nerlo-install-instruction
1 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/README.md · reported by nerlo-install-instruction
1 permissions-no-block
Files: settings.json · reported by agentshield