Loading the registry…
Block irreversible AI-agent actions before they run — deterministic, fail-closed action-veto (deny-list + exec-check + human-in-the-loop) for any tool-using agent, from a Claude Code hook to local LLMs.
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.
48 critical findings reported by cisco-skill-scanner, 24 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/BGMLAI/gate.cat, 287 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- gate.cat
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.
v2.0.11
178 findings · 15.7s
v0.3.74
37 findings · 21.1s
v0.1.0
8 findings · 6.8s
v0.1.0
17 findings · 6.8s
v0.1.0
0 findings · 14.1s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.2s
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 20, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-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 240 findings across every scanner that examined this package. 22 of 48 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 83 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.
44 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: YARA_command_injection_generic, YARA_sql_injection_generic, COMMAND_INJECTION_EVAL and 5 more · Files: /repo/tests/integrations/test_ephemeral_disarm.py, /repo/tests/test_freecore_toggle.py, /repo/tests/test_proxy_tool_veto.py and 25 more · reported by cisco-skill-scanner, agent-audit-kit
20 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: COMPOUND_FETCH_EXECUTE, opt.nerlo-rules.nerlo-install-pipe-to-shell, PIPELINE_TAINT_FLOW and 2 more · Files: /repo/docs/LAUNCH_0.4.16.md, /repo/docs/LAUNCH_KIT_2026-07-14.md, /repo/docs/SKILL.md and 4 more · reported by cisco-skill-scanner, nerlo-install-instruction
7 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: SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE, MANIFEST_INVALID_NAME · Files: /repo/docs/SKILL.md, /repo/docs/research/SKILL.md, /repo/examples/veto_integrations/claude_code_hook/SKILL.md · reported by cisco-skill-scanner
The model could have called any of these a false positive and did not.
25 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/gatecat/cloud_cli.py, /repo/gatecat/cloud_reporter.py, /repo/gatecat/plan_verifier.py and 9 more · reported by cisco-skill-scanner
16 YARA_system_manipulation_generic
Files: /repo/gatecat/integrations/bypass_suite.py, /repo/gatecat/integrations/guard.py, /repo/scripts/recall_danger_axis.py · reported by cisco-skill-scanner
12 COMMAND_INJECTION_EVAL
Files: /repo/gatecat/integrations/action_analysis.py, /repo/gatecat/integrations/input_guard.py, /repo/gatecat/integrations/policies.py and 4 more · reported by cisco-skill-scanner
10 YARA_command_injection_generic
Files: /repo/gatecat/integrations/bypass_suite.py, /repo/gatecat/integrations/guard.py, /repo/scripts/recall_danger_axis.py and 1 more · reported by cisco-skill-scanner
8 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/gatecat/audit.py, /repo/gatecat/branches.py, /repo/gatecat/cli.py and 4 more · reported by nerlo-behavioral
49 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: COMPOUND_FETCH_EXECUTE, COMPOUND_FIND_EXEC, AAK-IPI-WILD-CORPUS-001 and 9 more · Files: /repo/SKILL.md, RECALL.md, CHANGELOG.md and 19 more · reported by cisco-skill-scanner, agent-audit-kit, nerlo-install-instruction
31 The review call did not complete.
Rules: AAK-MCP-SDK-CVE-2026-52869-001, YARA_system_manipulation_generic, PIPELINE_TAINT_FLOW and 10 more · Files: uv.lock, /repo/gatecat/integrations/bypass_suite.py, /repo/docs/llms.txt and 15 more · reported by agent-audit-kit, cisco-skill-scanner
3 The model did not answer for these findings.
Rules: SOCIAL_ENG_VAGUE_DESCRIPTION · Files: /repo/SKILL.md, /repo/scripts/SKILL.md, /repo/ops/launch/SKILL.md · reported by cisco-skill-scanner
Artifact enables command injection and shell execution.
The artifact contains multiple critical command injection vulnerabilities, including `eval` and generic command injection patterns, found in files like `koryto.py`, `plan_verifier.py`, and various integration modules. It also exhibits capabilities for direct shell execution, resource abuse (fork bomb), and potential for credential access leading to network egress. High severity findings indicate system manipulation, pipeline taint flow, and further instances of credential exposure and shell execution via installation instructions. These capabilities are present across several core and integration components, posing significant risks.
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: scripts/corpus_recall.py, ops/deploy_landing.sh, gatecat/synthesis.py and 3 more · reported by agent-audit-kit
2 AAK-SKILL-UNTRUSTED-EXEC-PATH
Files: docs/install.sh, install.sh · reported by agent-audit-kit
2 PIPELINE_TAINT_FLOW
Files: /repo/gatecat/integrations/input_guard.py, /repo/gatecat/integrations/policies.py · reported by cisco-skill-scanner
2 RESOURCE_ABUSE_FORK_BOMB
Files: /repo/scripts/recall_danger_axis.py · reported by cisco-skill-scanner
1 AAK-MCP-OPENCLAW-CVE-2026-62195-001
Files: pyproject.toml · reported by agent-audit-kit
1 BINARY_FILE_DETECTED
Files: /repo/gatecat/integrations/models/injection_lr.npz · reported by cisco-skill-scanner
1 COMMAND_INJECTION_SHELL_TRUE
Files: /repo/gatecat/integrations/policies.py · reported by cisco-skill-scanner
Showing 16 of 16; the rest are in the per-scanner reports above.