akta-company-research
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed for read-only company and industry research. It does not contain any instructions for privilege escalation, persistence, or data exfiltration. All external interactions are managed through the SandBase gateway and vendor-specific tools (
akta_*), aligning with the author's identity. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted data from external sources, including employee reviews (
akta_company_employee_reviews), product feedback (akta_company_product_reviews), and news articles (akta_news). The skill mitigates this risk by explicitly instructing the agent to maintain a read-only workflow, cite sources, and separate factual observations from its own analysis.
Audit Metadata