static-analysis
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by ingesting untrusted source code and static analysis results (SARIF) which are then processed by the agent.
- Ingestion points: Target project files and SARIF output files (
results.sarif) analyzed inSKILL.md. - Boundary markers: The instructions lack explicit boundary markers or instructions to ignore embedded commands when processing these external data sources.
- Capability inventory: Shell command execution via the
Bashtool for running scanners and parsing results. - Sanitization: No explicit sanitization or validation of content within SARIF message fields is performed before the agent interprets the findings.
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to executecodeql,semgrep, andjqcommands. These operations are essential to the primary purpose of the skill but involve running commands based on the structure of the target codebase.
Audit Metadata