Loading the registry…
A deterministic policy firewall for AI agent tool calls — blocks, warns, or allows based on rules you write, not a risk score.
The publisher performed an authenticated act of publication — proving control of a namespace in the official MCP registry, or appearing in a first-party catalogue an operator curates. That establishes WHO published it. It is not a security finding, and attested artifacts carry Flagged verdicts too.
github: https://github.com/rudimentall1/agent-guardrail, 14 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- guardrail-mcp
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
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.
v2.0.11
9 findings · 6.8s
v0.3.26
3 findings · 1.0s
v0.1.0
0 findings · 26.7s
v0.1.0
0 findings · 26.7s
v0.71.0
0 findings · 0.2s
v2.3.8
0 findings · 1.2s
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
v0.71.0
No container image was published for this artifact. What each scanner covers
0 findings · 0.0s
vv1.6.0
No Go modules were found in this artifact. What each scanner covers
0 findings · 0.1s
No report in this scan: nerlo-multi-source.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 9, 2026 | Caution93 | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicabletrivy: completeosv-scanner: completetrivy_image ·n/a: not applicablegovulncheck ·n/a: not applicable | completed |
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 Caution badge are computed from those raw severities alone. Nothing below moved them.
Out of 12 findings across every scanner that examined this package.
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.
5 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-IPI-WILD-CORPUS-001, DATA_EXFIL_NETWORK_REQUESTS · Files: tests/test_default_policy.py, /repo/tests/test_confirmation_web_ui.py · reported by agent-audit-kit, 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.
2 COMPOUND_EXTRACT_EXECUTE
Files: /repo/PUBLISHING.md, /repo/SKILL.md · reported by cisco-skill-scanner
1 AAK-SEC-MD-001
Files: SECURITY.md · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: pyproject.toml · reported by agent-audit-kit
1 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md · reported by cisco-skill-scanner
1 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md · reported by cisco-skill-scanner
1 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/repo/CHANGELOG.md · reported by cisco-skill-scanner
Artifact contains high-severity code execution capabilities.
The artifact includes capabilities for compound extraction and execution, which warrant attention. It also exhibits undeclared network egress and supply chain risks. Further, a low-severity finding indicates a security markdown issue.
Concern level assessed by the review: High. 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.