sota-finder

Pass

Audited by Gen Agent Trust Hub on Nov 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted research data from external URLs and papers, which serves as an ingestion point for indirect prompt injection attacks.
  • Ingestion points: Data is retrieved from arbitrary external domains via the fetch_source.py script and the WebFetch tool.
  • Boundary markers: Absent. The instructions do not define explicit delimiters or instructions for the agent to ignore embedded commands within the research material.
  • Capability inventory: The agent has access to Bash for script execution, Write for artifact generation, and WebSearch/WebFetch for network access.
  • Sanitization: Present. The fetch_source.py script uses a ReadableHTMLParser to filter active content such as <script> and <style> tags. The build_outputs.py script uses html.escape to prevent XSS in the generated HTML reports.
  • [COMMAND_EXECUTION]: The skill executes internal utility scripts through the Bash tool.
  • Evidence: The SKILL.md file instructs the agent to run python3 "<skill-root>/scripts/fetch_source.py" and python3 "<skill-root>/scripts/build_outputs.py".
  • Risk: Potential for command injection exists if the agent interpolates user-controlled URLs or paths into the shell command without proper escaping, although the scripts themselves use argparse for argument handling.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 15, 2026, 10:07 AM