competitor-monitoring
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary function is to perform competitive intelligence using web-fetching tools. No malicious patterns, obfuscation, or unauthorized access attempts were found. The referenced URLs are for legitimate, well-known business services.
- [PROMPT_INJECTION]: The skill is designed to ingest and process data from external competitor websites, which presents a surface for indirect prompt injection.
- Ingestion points: Data retrieved from competitor pricing pages, blogs, and review sites via the WebFetch and WebSearch tools as described in the 'Monitoring Process' section of SKILL.md.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the fetched web content.
- Capability inventory: The skill uses WebFetch and WebSearch to read data, and it suggests integration with external skills (like cold-email-personalization) to initiate outreach.
- Sanitization: No explicit sanitization, validation, or instruction-filtering of external web content is described in the monitoring process.
Audit Metadata