competitor-monitor
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources including competitor websites, social media posts, and news articles.
- Ingestion points: Data is ingested via
firecrawl_scrape,exa_search,tavily_search, and various social media monitoring tools specified inSKILL.md. - Boundary markers: The instructions do not define specific delimiters to separate the external content from the agent's instructions, though they emphasize focusing on observable public behavior.
- Capability inventory: The skill's capabilities are restricted to information gathering and comparative analysis using provided tools; it does not have access to sensitive local files or arbitrary code execution.
- Sanitization: The skill does not explicitly describe sanitization or filtering of external content before processing.
Audit Metadata