ta-methods-writer
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it automatically reads and processes content from project files such as framework_.md and coding_.md.
- Ingestion points: Step 1 (Reading framework_.md and coding_.md).
- Boundary markers: None identified in the instructions to separate data from potential instructions.
- Capability inventory: Permission to write to the file system (methods.md) via the Write tool.
- Sanitization: No instructions to sanitize or validate the content of the files before processing.
- [COMMAND_EXECUTION]: The skill invokes a Write tool to save the generated methodology draft to a local file named methods.md.
Audit Metadata