competitive-market-research
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill workflow requires the agent to ingest and synthesize information from external, untrusted sources such as competitor websites, app store reviews, and documentation.
- Ingestion points: Workflow step 3 in
SKILL.mdidentifies external sources including websites, app stores, and review sites. - Boundary markers: The instructions lack explicit delimiters or warnings to the agent to treat external content strictly as data rather than instructions.
- Capability inventory: The skill relies on the agent's underlying ability to search, browse, and process external web content.
- Sanitization: No specific sanitization or data validation protocols are defined for the information retrieved from external platforms.
Audit Metadata