company-intel

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a research-oriented workflow designed to structure data gathering for product management and strategic analysis. It uses standard web search capabilities to access reputable public information sources.
  • [PROMPT_INJECTION]: The skill ingests data from external websites and search results during its research phase. While this represents a surface for indirect prompt injection (Category 8), the skill mitigates this by instructing the agent to cite sources, distinguish fact from inference, and organize data into a strict 11-section format. There are no attempts to override agent safety or system instructions.
  • [DATA_EXFILTRATION]: The skill processes company names and URLs provided by the user to perform legitimate research tasks. It targets well-known services and public databases such as LinkedIn, Glassdoor, Google Patents, and SEC filings for its data collection, which is consistent with its stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 03:54 AM
Security Audit — agent-trust-hub — company-intel