competitor-watch
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill is designed to ingest data from external, untrusted sources (e.g., TechCrunch, blogs, social media). ● Ingestion points: External news and public announcements via the create_scout tool. ● Boundary markers: Absent; the query template does not use delimiters to separate instructions from the data to be monitored. ● Capability inventory: Automated daily monitoring and reporting via create_scout; no direct command execution or file system access. ● Sanitization: None provided in the template instructions.
- No Executable Code (SAFE): The skill consists entirely of Markdown and metadata instructions for the agent. No scripts, binaries, or package dependencies were found.
Audit Metadata