ux-research
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from web search results.\n
- Ingestion points: Competitive research via web search (Step 3).\n
- Boundary markers: None identified in instructions to separate search content from agent logic.\n
- Capability inventory: The agent has file-write permissions to save results in .sage/work/ (Step 6).\n
- Sanitization: No explicit instructions for sanitizing or escaping content retrieved from external websites.
Audit Metadata