solo-customer-finder
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external public sources (forums, GitHub issues, and marketplace reviews) which could theoretically contain instructions intended to influence the agent's behavior.
- Ingestion points: Data is gathered via the
web_searchandweb_extracttools. - Boundary markers: The skill instructions do not explicitly mandate the use of delimiters when interpolating external quotes into the final report file.
- Capability inventory: The agent possesses
Writepermissions to thedocs/directory to save its research findings. - Sanitization: There are no specific instructions for escaping or sanitizing the harvested content before it is processed or written to disk.
- [SAFE]: The skill provides a link to a vendor-controlled repository (
github.com/fortunto2/searxng-docker-tavily-adapter) in the troubleshooting section as a suggestion for users wishing to self-host their own search infrastructure. This is documented neutrally as a resource provided by the author.
Audit Metadata