migration-skill
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- COMMAND_EXECUTION (LOW): The skill references and directs the execution of several internal Python scripts (e.g., analyze_project.py, validate_migration.py) to automate project analysis and documentation checks. These are local operations intended for the skill's primary purpose.
- PROMPT_INJECTION (LOW): Indirect Prompt Injection surface (Category 8) detected. 1. Ingestion points: Untrusted project data enters the context via grep and analysis scripts in USAGE.md. 2. Boundary markers: Absent. No delimiters or warnings isolate content extracted from code comments. 3. Capability inventory: The skill utilizes script execution (python3) and file system exploration. 4. Sanitization: No sanitization of extracted data is documented before agent processing.
Audit Metadata