Skills
Navigate
skills/gooseworks-ai/gooseworks-skills/icp-website-review/Gen Agent Trust Hub

icp-website-review

Pass

Audited by Gen Agent Trust Hub on Oct 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches and processes content from external, user-provided URLs which constitutes a surface for indirect prompt injection attacks.\n
  • Ingestion points: Website content is retrieved via WebFetch for multiple pages (homepage, pricing, product, etc.) and external data is gathered via WebSearch as described in Step 2 of SKILL.md.\n
  • Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions within the fetched content before processing.\n
  • Capability inventory: The agent can read local persona files from clients/<client>/personas/personas.json and write markdown reports to the local filesystem at clients/<client-name>/icp-reviews/.\n
  • Sanitization: The skill lacks explicit instructions for sanitizing or escaping the content retrieved from external websites before it is used to prompt the persona evaluations.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 10, 2026, 07:32 PM