metrics-dashboard
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious code, obfuscation, or high-risk behaviors were identified. The skill uses external links to a product management educational site (productcompass.pm) which are relevant to its stated purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read user-provided files such as analytics data or strategy docs. This creates a surface for indirect prompt injection if those files contain malicious instructions. However, the risk is negligible due to the limited capabilities of the skill. (1) Ingestion points: User-provided files mentioned in SKILL.md. (2) Boundary markers: Absent. (3) Capability inventory: The skill is restricted to reading provided files and generating a markdown dashboard specification; it lacks network access or shell execution tools. (4) Sanitization: Absent.
Audit Metadata