risk-heatmap

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill instructions or the provided script.
  • [COMMAND_EXECUTION]: The skill provides a Python script (scripts/generate_risk_heatmap.py) intended for the agent to execute. The script is self-contained, uses standard Python libraries, and includes input validation to ensure it processes valid risk data.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes untrusted user-supplied risk entries to generate an HTML report. This surface is assessed as safe based on the following:
  • Ingestion points: User-provided risk data (ID, name, description, owner, mitigation) is ingested by the scripts/generate_risk_heatmap.py script via command-line arguments or JSON files.
  • Boundary markers: No specific delimiters are required by the instructions, but data is handled through structured JSON processing.
  • Capability inventory: The script has the capability to write the generated report to a local file when an output path is provided via the --output flag.
  • Sanitization: The script correctly uses html.escape() for all interpolated user content (project name, risk IDs, names, categories, owners, and mitigation measures) before rendering the final HTML, effectively preventing Cross-Site Scripting (XSS) and related injection attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 12:27 PM
Security Audit — agent-trust-hub — risk-heatmap