Loading the registry…
AI running coach with progressive learning
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.
10 critical findings reported by cisco-skill-scanner, agent-audit-kit. 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 -- runnai
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- runnai ~/.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
2 findings · 1.2s
v2.0.11
234 findings · 11.8s
v0.3.74
14 findings · 7.4s
v0.1.0
15 findings · 7.7s
v0.1.0
0 findings · 7.7s
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 · 2.2s
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 20, 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 265 findings across every scanner that examined this package. None of the 10 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 31 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.
66 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: DATA_EXFIL_JS_FS_ACCESS, LOW_ANALYZABILITY, AAK-OAUTH-007 · Files: /repo/src/utils/__tests__/attach-reference-tool.test.ts, /repo/src/utils/__tests__/manage-plan-patch.test.ts, /repo/src/utils/__tests__/manage-plan-revise.test.ts and 11 more · reported by cisco-skill-scanner, agent-audit-kit
32 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/docs/superpowers/specs/SKILL.md, /repo/evals/fixtures/trail-prep/plans/SKILL.md and 13 more · reported by cisco-skill-scanner
2 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-prompt-extraction-412 · Files: CLAUDE.md, .claude/CLAUDE.md · reported by agentshield
The model could have called any of these a false positive and did not.
83 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/evals/mcp-stdio-server.ts, /repo/src/cli/App.tsx, /repo/src/cli/commands.ts and 21 more · reported by cisco-skill-scanner
15 DATA_EXFIL_JS_NETWORK
Files: /repo/src/intervals/client.ts, /repo/src/strava/client.ts, /repo/src/tools/weather.ts and 1 more · reported by cisco-skill-scanner
11 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/src/intervals/client.ts, /repo/src/strava/client.ts · reported by nerlo-behavioral
9 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/evals/provider.mjs, /repo/evals/run-agent.ts, /repo/src/cli/commands.ts and 3 more · reported by cisco-skill-scanner
4 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/src/strava/client.ts · reported by nerlo-behavioral
3 FILE_MAGIC_MISMATCH
29 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: AAK-MCP-015, DATA_EXFIL_JS_FS_ACCESS, AAK-ANTHROPIC-SDK-001 and 6 more · Files: evals/mcp-stdio-server.ts, /repo/evals/generate-fixtures.ts, /repo/evals/run-agent.ts and 18 more · reported by agent-audit-kit, cisco-skill-scanner
2 The model did not answer for these findings.
Rules: DATA_EXFIL_JS_FS_ACCESS, AAK-MCP-018 · Files: /repo/src/utils/__tests__/plan-parser.test.ts, evals/mcp-stdio-server.ts · reported by cisco-skill-scanner, agent-audit-kit
Artifact allows shell execution and data exfiltration.
The artifact contains critical findings for command injection, enabling shell execution within its utility functions, CLI components, and evaluation scripts. High-severity findings also indicate extensive capabilities for file system access, network egress, and potential exposure of credentials through network transmission. These risks are present in core application logic and development-related files.
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.
2 AAK-OAUTH-006
Files: src/strava/client.ts, src/strava/oauth-server.ts · reported by agent-audit-kit
1 AAK-LEGAL-002
Files: package.json · reported by agent-audit-kit
1 AAK-OAUTH-007
Files: src/strava/client.ts · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: package.json · reported by agent-audit-kit
1 AAK-SECRET-004
Files: src/intervals/client.ts · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: package.json · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 LOW_ANALYZABILITY
Files: /repo · reported by cisco-skill-scanner
Showing 13 of 13; the rest are in the per-scanner reports above.