competitor-profiling
Pass
Audited by Gen Agent Trust Hub on May 2, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill ingests untrusted data from competitor websites and review platforms via scraping tools. This creates a surface for indirect prompt injection where malicious content on a scanned site could attempt to influence the agent's behavior. However, the risk is mitigated by the skill's limited capabilities and intended use case.
- Ingestion points: Scraped content from external competitor URLs (SKILL.md).
- Boundary markers: Not utilized in the synthesized profile templates.
- Capability inventory: Writing markdown files to the local 'competitor-profiles/' project directory (SKILL.md).
- Sanitization: No explicit content filtering or validation is defined.
- [EXTERNAL_DOWNLOADS]: The skill utilizes the Firecrawl and DataForSEO services to fetch website data and marketing metrics. These interactions are standard for competitive research and target established service providers.
Audit Metadata