factory-explain
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted codebase content to generate explanations, creating a surface for indirect prompt injection. 1. Ingestion points: Codebase folders and build plans analyzed by the skill. 2. Boundary markers: No specific delimiters or instructions to ignore embedded commands are present. 3. Capability inventory: The skill writes generated content to factory/GUIDE.md and updates STATE.md. 4. Sanitization: No content sanitization or validation of the input code is specified before processing.
- [COMMAND_EXECUTION]: The skill performs local file system operations, specifically creating or appending to factory/GUIDE.md and modifying STATE.md to track progress and store documentation. These operations are restricted to the local workspace and align with the skill's described purpose.
Audit Metadata