report-generator

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface where untrusted data from external files is processed and reflected into generated HTML files without escaping.
  • Ingestion points: Data is loaded from files in scripts/main.py via the generate and weekly commands using json.loads() and csv.DictReader().
  • Boundary markers: The skill does not use specific delimiters or instructions to prevent the agent from following potential commands hidden within the data files.
  • Capability inventory: The skill possesses file-system read and write capabilities, allowing it to read arbitrary data files and write generated reports to specified paths.
  • Sanitization: The generate_report_html and generate_weekly_html functions in scripts/main.py perform direct string interpolation using f-strings. There is no evidence of HTML escaping or sanitization of metric names, titles, or data values, which allows raw HTML/JS to be written to the output file.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:16 PM
Security Audit — agent-trust-hub — report-generator