competitor-discovery
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches and processes content from external, untrusted competitor websites to extract business summaries and target audience signals. * Ingestion points: Competitor homepages and pricing pages are retrieved in Step 4 of the process. * Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard potential commands embedded within the fetched website content. * Capability inventory: The agent has the ability to perform web searches and fetch arbitrary URLs discovered during the search process. * Sanitization: No sanitization or filtering of the retrieved web content is specified before the agent processes it for analysis.
Audit Metadata