agent-governance-assistant@5.0.3
VERIFIED· install onlyPublisher claims: "UPDATED 2026: Covers China AI Agent governance regulations (generative AI regulations), MCP protocol governance implications, and enterprise AI audit frameworks. AI-powered enterprise AI agent governance framework — audit agent behavior, enforce security policies, ensure CBIRC/CFCA compliance, detect shadow AI, and generate governance reports. Built for IT risk managers, compliance officers, and enterprise AI leaders in financial institutions. Keywords: AI agent governance, enterprise AI, agent compliance, AI security policy, CBIRC, CFCA, shadow AI detection, agent audit, Microsoft Agent 365, Copilot Studio, China AI regulation, Agent治理, 企业AI, AI合规, 影子AI检测, AI审计, NFRA AI合规, AI治理." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What changed since 5.0.2
vet-skills diff agent-governance-assistant 5.0.2 5.0.3In the sandbox, this version reached for nothing 5.0.2 did not. Compared from the two recorded runs, not from source.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-16 and scored it 95/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
No findings across 560 lines in 1 files.
Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.