competitor-monitoring
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external, untrusted sources which could lead to manipulation of the agent's output or actions.
- Ingestion points: The agent uses the Chrome MCP to visit competitor homepages, product pages, pricing pages, and blogs, as defined in a competitor list file read from Google Drive (SKILL.md).
- Boundary markers: The instructions lack specific delimiters or guardrails to prevent the agent from interpreting instructions that might be hidden within the HTML or text of the websites it visits.
- Capability inventory: The skill possesses file-writing capabilities to Google Drive via the Google Drive MCP, which is used to save the final research reports.
- Sanitization: No sanitization or validation mechanisms are described to filter out potentially malicious content or instructions embedded in the external web data before processing.
Audit Metadata