akta-company-research
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified during the analysis of this skill.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data such as company enrichment info, employee reviews, and product feedback, which represents an ingestion surface for untrusted content.
- Ingestion points: External company, employee, and product data retrieved via the
akta_*tool suite. - Boundary markers: The skill includes instructions to "Cite sources and preserve attribution" and "Separate factual observations from analysis," which serve as functional boundaries to ensure data is treated as information rather than instructions.
- Capability inventory: The skill is restricted to information retrieval tools (
akta_company_enrichment,akta_company_employee_reviews,akta_company_product_reviews,akta_company_search,akta_industry_search,akta_news) invoked through the standard platform tool caller. - Sanitization: No explicit sanitization or filtering of external content is defined in the instructions, but the skill is explicitly limited to "Read-only research" and prohibits taking actions on external platforms.
Audit Metadata