Loading the registry…
AI multi-model consensus engine for software supply chain security
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.
51 critical findings reported by cisco-skill-scanner, agent-audit-kit, 7 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/iml1s/aigate, 270 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 -- aigate
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
8 findings · 0.8s
v2.0.11
187 findings · 19.7s
v0.3.74
12 findings · 21.3s
v0.1.0
0 findings · 6.5s
v0.1.0
50 findings · 6.5s
v0.1.0
0 findings · 9.8s
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 22, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-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 257 findings across every scanner that examined this package. 44 of 51 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 2 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.
127 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: COMMAND_INJECTION_EVAL, DATA_EXFIL_HTTP_POST, PATH_TRAVERSAL_OPEN and 16 more · Files: /repo/tests/fixtures/fake_injection_attempts.py, /repo/tests/fixtures/fake_malicious_litellm.py, /repo/tests/fixtures/fake_malicious_ua_parser.py and 51 more · reported by cisco-skill-scanner, agent-audit-kit
74 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, PIPELINE_TAINT_FLOW, PROMPT_INJECTION_IGNORE_INSTRUCTIONS and 6 more · Files: /repo/docs/ai-tool-integration.md, /repo/docs/attack-detection.md, /repo/docs/plans/2026-03-28-complete-missing-features.md and 10 more · reported by nerlo-install-instruction, cisco-skill-scanner
4 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-AGENT-TRUST-002, AAK-AGENT-TRUST-001, AAK-GHA-IMMUTABLE-001 · Files: .github/workflows/claude.yml, .github/workflows/claude-code-review.yml · reported by agent-audit-kit
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: TOOL_ABUSE_UNDECLARED_NETWORK, MANIFEST_INVALID_NAME · Files: /repo/repo/AGENTS.md, /repo/.github/SKILL.md · reported by 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.
8 MANIFEST_MISSING_LICENSE
Files: /repo/.claude/skills/add-backend/SKILL.md, /repo/.claude/skills/aigate-scan/SKILL.md, /repo/.claude/skills/verify/SKILL.md and 5 more · reported by cisco-skill-scanner
4 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/.claude/skills/release/SKILL.md, /repo/CONTRIBUTING.md, /repo/README.md · reported by nerlo-install-instruction
4 PIPELINE_TAINT_FLOW
Files: /repo/SKILL.md, /repo/README.md · reported by cisco-skill-scanner
4 YARA_prompt_injection_generic
Files: /repo/src/aigate/sandbox/__init__.py, /repo/src/aigate/sandbox/errors.py, /repo/src/aigate/sandbox/types.py · reported by cisco-skill-scanner
3 COMMAND_INJECTION_EVAL
Files: /repo/src/aigate/prefilter.py, /repo/src/aigate/sandbox/types.py · reported by cisco-skill-scanner
3 HIDDEN_DATA_FILE
Files: /repo/.windsurfrules, /repo/.clinerules, /repo/.omc/research/birdcage-output-shape.md · reported by cisco-skill-scanner
3 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/README.md · reported by nerlo-install-instruction
3 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/.claude/skills/check-package/SKILL.md, /repo/SKILL.md, /repo/.omc/research/SKILL.md · reported by cisco-skill-scanner
2 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/src/aigate/prefilter.py · reported by cisco-skill-scanner
1 AAK-MCP-NOAUTH-DEFAULT
Files: src/aigate/enrichment/context7.py · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: pyproject.toml · reported by agent-audit-kit
1 DATA_EXFIL_SENSITIVE_FILES
Files: /repo/src/aigate/sandbox/canary.py · reported by cisco-skill-scanner
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 hooks-chained-commands-0
Files: settings.json · reported by agentshield
1 hooks-silent-fail-111
Files: settings.json · reported by agentshield
1 hooks-silent-fail-126
Files: settings.json · reported by agentshield
1 hooks-silent-fail-148
Files: settings.json · reported by agentshield
1 hooks-silent-fail-163
Files: settings.json · reported by agentshield
1 hooks-silent-fail-211
Files: settings.json · reported by agentshield
1 hooks-silent-fail-226
Files: settings.json · reported by agentshield
1 opt.nerlo-rules.nerlo-cursor-conceal-from-user
Files: /repo/.cursorrules · reported by nerlo-install-instruction
1 permissions-no-block
Files: settings.json · reported by agentshield
1 PROMPT_INJECTION_IGNORE_INSTRUCTIONS
Files: /repo/SKILL.md · reported by cisco-skill-scanner
2 The model gave no reason we were willing to publish, and a verdict without one is not usable evidence.
Rules: FILE_MAGIC_MISMATCH · Files: /repo/tests/fixtures/fake_malicious_ua_parser.py, /repo/tests/fixtures/fake_malicious_crossenv.py · reported by cisco-skill-scanner
Critical command injection and prompt manipulation risks
The artifact contains critical command injection vulnerabilities in `/repo/src/aigate/prefilter.py` and `/repo/src/aigate/sandbox/types.py`, allowing for shell execution. It also has critical prompt injection findings in `/repo/src/aigate/sandbox/__init__.py`, `/repo/src/aigate/sandbox/errors.py`, and `/repo/src/aigate/sandbox/types.py`. Additionally, there is a high-severity finding for data exfiltration of sensitive files from `/repo/src/aigate/sandbox/canary.py` and unauthenticated access in `src/aigate/enrichment/context7.py`.
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.