competitor-research
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill utilizes the vendor's own CLI tool ('orth') to interact with research APIs (brand-dev, exa, fiber, scrapegraph). This is consistent with the skill's stated purpose of competitor intelligence gathering.
- [INDIRECT_PROMPT_INJECTION]: The skill performs web scraping and search operations (via 'scrapegraph' and 'exa'). While this allows external data to enter the agent's context, which is a common surface for indirect prompt injection, it is necessary for the skill's primary function. There are no high-risk capabilities (like file system modification or credential access) associated with this data ingestion.
Audit Metadata