auditing-repository-health
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/audit_repository_health.pyutilizessubprocess.run()to execute shell commands during its analysis phase. This is used to detect project boundaries, language ecosystems, and Git metadata. This behavior is standard for a tool designed to analyze repository environments. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests and processes data from the repository being audited.
- Ingestion points:
audit_repository_health.pyreads various repository files (e.g., package manifests, CI workflows, and documentation) provided via the--repoargument. - Boundary markers: No explicit boundary markers or instructions to ignore embedded prompts were identified in the skill's instructions.
- Capability inventory: The script possesses capabilities for file system access and system command execution (
subprocess.run). - Sanitization: No explicit sanitization or filtering of the audited repository content is documented.
Audit Metadata