competitor-profiling
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external websites and review platforms (such as G2 and Capterra) using Firecrawl. This content is then used to synthesize competitor profiles, creating a surface for indirect prompt injection where an attacker could influence the agent's output or logic by placing malicious instructions on the target sites.
- Ingestion points: Competitor URLs provided by the user, URLs discovered via site mapping, and external review platforms (SKILL.md).
- Boundary markers: The instructions do not specify any delimiters or safety warnings (like 'ignore embedded instructions') when processing the scraped content.
- Capability inventory: The skill has the ability to write files to the local file system (competitor-profiles/ directory) and perform further network lookups via DataForSEO tools.
- Sanitization: No specific sanitization or validation of the scraped markdown content is mentioned before it is processed by the AI.
Audit Metadata