market-research-reports

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's logic and instructions are entirely consistent with its described functionality. No malicious behaviors, data exfiltration, or safety bypasses were detected.
  • [COMMAND_EXECUTION]: The batch generation script in scripts/generate_market_visuals.py executes commands to invoke other visual skills. This is implemented using safe subprocess calls that pass arguments as a list, mitigating command injection risks.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection due to its use of a research-lookup tool to fetch external data. However, there are no instructions to bypass safety guidelines, and the risk is inherent to the intended research functionality. Ingestion point: research-lookup output. Boundary markers: none. Capability inventory: Bash, Read, Write, Edit. Sanitization: none.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 08:22 AM
Security Audit — agent-trust-hub — market-research-reports