sec-track
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from security finding files (e.g., findings.json), which may contain content from external, untrusted sources. This data is interpolated into command arguments for ticket creation and issue reporting.
- Ingestion points: The skill reads from findings.json to extract finding IDs, titles, and locations.
- Boundary markers: The instructions do not specify strict delimiters for the interpolated content, though they recommend a human review of the generated preview.
- Capability inventory: The skill utilizes the GitHub CLI (gh) for network operations and calls Python scripts (ticket_writer.py, secfind.py) for file modifications.
- Sanitization: No explicit sanitization or escaping of the finding data is mentioned.
- [COMMAND_EXECUTION]: The skill requires the execution of multiple CLI tools and scripts to perform its tasks, including gh issue create, gh api, and custom Python scripts located in adjacent directories (ticket-master, sec-scan).
Audit Metadata