writing-plans
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill generates implementation plans that include executable Python code and shell commands based on external specifications.
- Ingestion points: User-provided specifications and requirements enter the context as described in the Overview.
- Boundary markers: No explicit delimiters or instructions are used to prevent the agent from obeying malicious instructions embedded within the user's specs.
- Capability inventory: The skill generates code and command sequences (e.g., git, pytest) intended to be run by execution sub-skills like powers:executing-plans.
- Sanitization: The skill lacks mechanisms to validate or filter input requirements before including them in the implementation tasks.
Audit Metadata