Loading the registry…
Company AI coding guardrails based on Ponytail.
Gemini Extensions are packaged skills loaded into Gemini; 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.
37 critical findings reported by cisco-skill-scanner, agent-audit-kit, 29 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
Gemini Extensions install to a single target, no runtime picker.
nerlo install -- panda-company-plugin
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
5 findings · 0.6s
v2.0.11
234 findings · 12.0s
v0.3.74
20 findings · 3.4s
v0.1.0
10 findings · 4.3s
v0.1.0
0 findings · 4.3s
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 · 1.8s
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: 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 269 findings across every scanner that examined this package. 8 of 37 findings rated critical by their scanner were among the dismissals.
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.
71 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_JS_CHILD_PROCESS, DATA_EXFIL_JS_FS_ACCESS, FILE_MAGIC_MISMATCH · Files: /repo/tests/hermes-plugin.test.js, /repo/tests/hooks-windows.test.js, /repo/tests/hooks.test.js and 12 more · reported by cisco-skill-scanner
7 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, MANIFEST_INVALID_NAME · Files: /repo/.github/SKILL.md, /repo/docs/SKILL.md, /repo/examples/SKILL.md · reported by cisco-skill-scanner
5 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: AAK-AGENT-003, AAK-HEALTHCARE-AI-004, TOOL_ABUSE_UNDECLARED_NETWORK · Files: AGENTS.md, .github/copilot-instructions.md, /repo/repo/AGENTS.md · reported by agent-audit-kit, cisco-skill-scanner
1 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-MARKETPLACE-001 · Files: .github/plugin/marketplace.json · 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.
44 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/.opencode/plugins/ponytail-frontmatter.cjs, /repo/.opencode/plugins/ponytail.mjs, /repo/benchmarks/arms/caveman.js and 14 more · reported by cisco-skill-scanner
24 HIDDEN_DATA_FILE
Files: /repo/.opencode/command/panda.md, /repo/.opencode/plugins/ponytail-frontmatter.cjs, /repo/.openclaw/skills/panda-review/SKILL.md and 21 more · reported by cisco-skill-scanner
19 MANIFEST_MISSING_LICENSE
Files: /repo/skills/panda/SKILL.md, /repo/skills/panda-debt/SKILL.md, /repo/skills/panda-audit/SKILL.md and 16 more · reported by cisco-skill-scanner
16 COMMAND_INJECTION_EVAL
Files: /repo/benchmarks/correctness.js, /repo/benchmarks/robustness-audit.js · reported by cisco-skill-scanner
16 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/benchmarks/agentic/judge.py, /repo/benchmarks/agentic/tasks.py, /repo/benchmarks/benchmark-local.py · reported by cisco-skill-scanner
Artifact has critical command injection and data exfiltration risks.
The artifact contains multiple critical command injection vulnerabilities, particularly in JavaScript files like `/repo/benchmarks/correctness.js` and `/repo/benchmarks/robustness-audit.js`, and a critical finding in `benchmarks/agentic/tasks.py`. It also exhibits high-severity data exfiltration capabilities, including file system access and potential secret exposure to network egress. These findings indicate the artifact can execute arbitrary commands and transmit sensitive data.
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.
12 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/benchmarks/correctness.js, /repo/benchmarks/robustness-audit.js, /repo/scripts/publish-openclaw-skills.js · reported by cisco-skill-scanner
11 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/.clinerules/SKILL.md, /repo/ponytail-mcp/SKILL.md and 8 more · reported by cisco-skill-scanner
7 AAK-HEALTHCARE-AI-004
Files: .clinerules/panda.md, .openclaw/skills/panda/SKILL.md, .qoder/rules/panda.md and 4 more · reported by agent-audit-kit
6 DATA_EXFIL_JS_NETWORK
Files: /repo/benchmarks/claude-email.js, /repo/benchmarks/model-email.js, /repo/benchmarks/robustness-audit.js · reported by cisco-skill-scanner
4 LOW_ANALYZABILITY
Files: /repo/benchmarks/arms, /repo/benchmarks, /repo/ponytail-mcp and 1 more · reported by cisco-skill-scanner
3 AAK-MARKETPLACE-001
Files: .grok-plugin/marketplace.json, .claude-plugin/marketplace.json, .agents/plugins/marketplace.json · reported by agent-audit-kit
3 hooks-no-stop-hooks
Files: hooks/claude-codex-hooks.json, hooks/copilot-hooks.json, hooks/qoder-hooks.json · reported by agentshield
3 opt.nerlo-rules.nerlo-dynamic-exec
Files: /repo/benchmarks/correctness.js, /repo/benchmarks/robustness-audit.js · reported by nerlo-behavioral
3 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/benchmarks/claude-email.js, /repo/benchmarks/model-email.js, /repo/benchmarks/robustness-audit.js · reported by nerlo-behavioral
3 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/benchmarks/claude-email.js, /repo/benchmarks/model-email.js, /repo/benchmarks/robustness-audit.js · reported by nerlo-behavioral
2 hooks-no-pretooluse
Files: hooks/claude-codex-hooks.json, hooks/copilot-hooks.json · reported by agentshield
1 AAK-IPI-WILD-CORPUS-001
Files: benchmarks/arms/caveman-SKILL.md · reported by agent-audit-kit
1 AAK-LEGAL-002
Files: pi-extension/package.json · reported by agent-audit-kit
1 AAK-MCP-015
Files: benchmarks/agentic/tasks.py · reported by agent-audit-kit
1 AAK-MCP-018
Files: ponytail-mcp/index.js · 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 MANIFEST_INVALID_NAME
Files: /repo/.clinerules/SKILL.md · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/benchmarks/agentic/judge.py · reported by nerlo-behavioral
1 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/benchmarks/repo/benchmarks/README.md · reported by cisco-skill-scanner
Showing 25 of 88; the rest are in the per-scanner reports above.