skill-forge-build
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input (plans or descriptions) to generate code and scripts.\n
- Ingestion points: Processes plan documents, natural language descriptions, and existing skills (SKILL.md).\n
- Boundary markers: The instructions do not explicitly include delimiters or instructions to ignore potential injection within user-provided plans.\n
- Capability inventory: The skill generates Python scripts, shell installers (install.sh), and executes validation tools.\n
- Sanitization: No specific sanitization or validation of the input content is described before it is used to scaffold new files.\n- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute specific local scripts.\n
- Evidence: Instructions include running 'python scripts/init_skill.py' for scaffolding and 'python scripts/validate_skill.py' for quality checks.
Audit Metadata