Loading the registry…
AI Agent Training Repository for Non-Engineers
Cursor Rules are .cursorrules / .cursor/rules files that steer Cursor's AI; 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.
9 critical findings reported by agent-audit-kit, 5 of them in the installed artifact. 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/minicoohei/ai-agent-camp, 945 findings
Cursor Rules are .cursorrules / .cursor/rules files that steer Cursor's AI. Review the scanned source before copying them into your own project.
nerlo install -- ai-agent-camp
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.
v1.4.0
221 findings · 3.4s
v2.0.11
Timed out
0 findings · 300.0s
v0.3.74
50 findings · 173.5s
v0.1.0
51 findings · 48.1s
v0.1.0
42 findings · 48.2s
v0.1.0
0 findings · 53.3s
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 ·!: timeoutagent-audit-kit: completenerlo-behavioral: completenerlo-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 364 findings across every scanner that examined this package. 1 of 9 findings rated critical by their scanner was among the dismissals.
Not reviewed is not the same as clean. Those 195 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.
7 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-LLM-SQL-RCE-001, AAK-TASKS-003, AAK-OAUTH-007 · Files: tests/tools/test_ugc_pipeline.py, tests/skills/test_check_inbox_slack_parser.py, tests/skills/test_check_inbox_common.py and 4 more · reported by agent-audit-kit
4 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: opt.nerlo-rules.nerlo-install-pipe-to-shell, opt.nerlo-rules.nerlo-install-fetch-raw-then-run · Files: /repo/docs/terminal-guide.md, /repo/docs/troubleshoot.md · reported by nerlo-install-instruction
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: agents-destructive-tool-1111 · Files: CLAUDE.md · reported by agentshield
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.
29 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/.claude/skills/check-inbox/scripts/line_notifier.py, /repo/.claude/skills/video-analyzer/scripts/analyze_video.py, /repo/.claude/skills/video-audio/scripts/generate_audio.py and 16 more · reported by nerlo-behavioral
22 opt.nerlo-rules.nerlo-dynamic-exec
Files: /repo/mv-composer/scripts/gen_bgm_tax.mjs, /repo/mv-composer/scripts/generate_bgm.mjs, /repo/mv-composer/scripts/generate_bgm2.mjs and 3 more · reported by nerlo-behavioral
20 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/.claude/skills/youtube-clipper/SKILL.en.md, /repo/.claude/skills/youtube-clipper/SKILL.es.md, /repo/.claude/skills/youtube-clipper/SKILL.md and 7 more · reported by nerlo-install-instruction
13 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/.claude/commands/lesson/setup-bigquery.en.md, /repo/.claude/commands/lesson/setup-gogcli.en.md, /repo/.claude/commands/lesson/start-0-1.en.md and 10 more · reported by nerlo-install-instruction
10 hooks-silent-fail-42
The model could have called any of these a false positive and did not.
2 AAK-OAUTH-008
Files: tests/tools/test_run_lesson_14_11.py, examples/final/module-10-notion/notion_integration.py · reported by agent-audit-kit
2 AAK-SECRET-004
Files: tests/tools/test_credential_manager.py, examples/final/module-06-search/slack_search.py · reported by agent-audit-kit
152 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: skills-missing-governance-.claude/commands/module-18-gcp-appendix.md, skills-missing-governance-commands/module-24-soql.md, skills-missing-telemetry-.claude/commands/module-18-google-auth.es.md and 149 more · Files: .claude/commands/module-18-gcp-appendix.md, commands/module-24-soql.md, .claude/commands/module-18-google-auth.es.md and 89 more · reported by agentshield
43 The review budget for this scan was already spent before these findings were reached.
Rules: skills-missing-governance-commands/verify-module.md, skills-missing-telemetry-.claude/commands/module-24-metadata-retrieve.md, skills-missing-governance-.claude/commands/module-18-gcp-quick.es.md and 39 more · Files: commands/verify-module.md, .claude/commands/module-24-metadata-retrieve.md, .claude/commands/module-18-gcp-quick.es.md and 36 more · reported by agentshield, agent-audit-kit, nerlo-install-instruction
Artifact contains critical remote code execution and untrusted skill execution vulnerabilities.
The artifact includes critical vulnerabilities for SQL remote code execution in `mv-composer/scripts` and `tools/ugc/engines` files, and untrusted skill execution in `skills/youtube-clipper/SKILL.md` and `skills/aiagent-tooling-setup/SKILL.md`. Additionally, there are high-severity findings for dynamic code execution, potential secret exposure in various test and utility scripts, and untrusted execution paths in `tools/scripts/setup.py` and `tools/scripts/setup.sh`. The artifact also exhibits network egress capabilities when secrets are present.
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: settings.json, .claude/settings.json · reported by agentshield
6 AAK-HEALTHCARE-AI-004
Files: .claude/skills/copy-editing/SKILL.md, .claude/skills/copy-editing/SKILL.en.md, .claude/skills/seo-audit/references/aeo-geo-patterns.md and 3 more · reported by agent-audit-kit
5 AAK-LLM-SQL-RCE-001
Files: tools/ugc/engines/longcat.py, tools/ugc/engines/veo.py, tools/ugc/engines/kling.py and 2 more · reported by agent-audit-kit
4 AAK-TASKS-003
Files: tools/extract_tasks.py, tools/howtodo_generator.py, .claude/skills/check-inbox/scripts/common.py and 1 more · reported by agent-audit-kit
3 AAK-IPI-WILD-CORPUS-001
Files: .claude/commands/lesson/setup-vercel.en.md, .cursor/commands/utility/update-plugins.en.md, .cursor/commands/lesson/setup-vercel.en.md · reported by agent-audit-kit
3 AAK-OAUTH-007
Files: credentials/google-workspace-desktop-oauth.json, tools/google_api_setup.py, data/slack-sync/scripts/get_token.py · reported by agent-audit-kit
3 AAK-SECRET-004
Files: tools/generate_reference_docs.py, courses/aiagent/lesson02-setup/ch03-api-settings/final/test-script.py, tools/cli_mode_check/migrate.py · reported by agent-audit-kit
3 AAK-SKILL-001
Files: .claude/skills/youtube-clipper/SKILL.md, skills/aiagent-tooling-setup/SKILL.md, skills/youtube-clipper/SKILL.md · reported by agent-audit-kit
2 AAK-LEGAL-002
Files: package.json, mv-composer/package.json · reported by agent-audit-kit
2 AAK-OAUTH-005
Files: .claude/skills/content-optimizer/scripts/collect_metrics.py, skills/content-optimizer/scripts/collect_metrics.py · reported by agent-audit-kit
2 AAK-SKILL-UNTRUSTED-EXEC-PATH
Files: tools/scripts/setup.py, tools/scripts/setup.sh · reported by agent-audit-kit
2 AAK-SPLUNK-TOKLOG-001
Files: .claude/skills/x-research/scripts/x_research.py, skills/x-research/scripts/x_research.py · reported by agent-audit-kit
2 hooks-logging-disabled-585
Files: hooks/console-log-guard.sh, .claude/hooks/console-log-guard.sh · reported by agentshield
2 hooks-logging-disabled-592
Files: hooks/git-push-review.sh, .claude/hooks/git-push-review.sh · reported by agentshield
2 hooks-logging-disabled-728
Files: hooks/console-log-guard.sh, .claude/hooks/console-log-guard.sh · reported by agentshield
2 hooks-no-stop-hooks
Files: settings.json, .claude/settings.json · reported by agentshield
2 opt.nerlo-rules.nerlo-install-fetch-raw-then-run
Files: /repo/courses/aiagent/lesson02-setup/ch01-environment/practice/setup-guide.md, /repo/courses/aiagent/lesson02-setup/ch01-environment/practice/troubleshooting.md · reported by nerlo-install-instruction
2 permissions-missing-deny->-/dev/
Files: settings.json, .claude/settings.json · reported by agentshield
2 permissions-missing-deny-chmod-777
Files: settings.json, .claude/settings.json · reported by agentshield
2 permissions-missing-deny-ssh
Files: settings.json, .claude/settings.json · reported by agentshield
1 AAK-OAUTH-006
Files: data/slack-sync/scripts/get_token.py · reported by agent-audit-kit
1 AAK-TASKS-002
Files: tools/howtodo_generator.py · reported by agent-audit-kit
1 hooks-no-pretooluse
Files: courses/aiagent/lesson02-setup/ch02-extensions/final/settings.json · reported by agentshield
1 opt.nerlo-rules.nerlo-install-destructive-system-command
Files: /repo/.cursor/rules/shell-safety.mdc · reported by nerlo-install-instruction
1 opt.nerlo-rules.nerlo-install-shell-inline-command
Files: /repo/courses/aiagent/lesson02-setup/ch01-environment/practice/setup-guide.md · reported by nerlo-install-instruction
1 permissions-no-block
Files: courses/aiagent/lesson02-setup/ch02-extensions/final/settings.json · reported by agentshield
1 skills-missing-governance-skills/README.md
Files: skills/README.md · reported by agentshield
1 skills-missing-telemetry-skills/README.md
Files: skills/README.md · reported by agentshield
Showing 25 of 101; the rest are in the per-scanner reports above.