metrics-tagging
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided content including UI screenshots, prototype frames, and text descriptions to produce analytics taxonomies and update a local registry file.\n
- Ingestion points: Processes images and text provided by the user (designers) as described in SKILL.md.\n
- Boundary markers: Instructions do not define boundary markers or 'ignore embedded instructions' warnings for the analyzed content.\n
- Capability inventory: The skill performs file read and append operations on the local file 'references/event-registry.md' (SKILL.md).\n
- Sanitization: Instructions recommend avoiding PII in properties but lack mechanisms to prevent prompt injection payloads within mockup text from influencing the agent's output.\n- [EXTERNAL_DOWNLOADS]: The README provides installation instructions using 'npx' to download content from the vendor-owned repository 'ommakes/Skills'.
Audit Metadata