privacy-policy
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to visit and research a user-provided $PRODUCT_URL to map out data collection practices, which introduces a vulnerability surface for indirect prompt injection.
- Ingestion points: External content retrieved from the $PRODUCT_URL mentioned in SKILL.md.
- Boundary markers: Absent. The instructions do not specify any delimiters or warnings to the agent to disregard instructions found within the fetched content.
- Capability inventory: Web browsing tools are used to access external network resources.
- Sanitization: Absent. There is no mechanism described for filtering or sanitizing content retrieved from the external URL.
Audit Metadata