company-contact-finder
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external databases (Crustdata and SixtyFour). While this introduces an attack surface where malicious content could be embedded in profile data, the risk is negligible as the skill lacks destructive capabilities.
- Ingestion points: API responses from
mcp__gooseworks__crustdata_nl_search,mcp__gooseworks__crustdata_search, andmcp__gooseworks__sixtyfour_nl_search(SKILL.md). - Boundary markers: Absent; results are interpolated directly into display tables and JSON structures.
- Capability inventory: Limited to data deduplication and formatting (table/JSON). No file system access, command execution, or generic network tools are utilized.
- Sanitization: Absent; the skill does not explicitly filter or escape content from search results.
Audit Metadata