privacy-policy
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to process content from external websites, which are untrusted sources. This activity creates a surface for indirect prompt injection attacks where hidden instructions in the analyzed web pages could affect the agent's behavior.\n
- Ingestion points: Website HTML and privacy policy pages described in the 'Check' section of SKILL.md.\n
- Boundary markers: None present.\n
- Capability inventory: The skill does not provide tools or scripts, but the agent's environment likely enables web browsing.\n
- Sanitization: Not addressed.\n- [SAFE]: No obfuscation, hardcoded credentials, or remote code execution patterns were detected. The skill uses reputable external resources and adheres to standard privacy audit practices.
Audit Metadata