materialize
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill treats user-supplied commit titles and descriptions as authoritative instructions for codebase modifications.
- Ingestion points: Arguments provided to the
/materializecommand in SKILL.md. - Boundary markers: None present. The instructions explicitly mandate that the agent "do not ask for clarification" and treat the input as the sole specification.
- Capability inventory: The skill allows the agent to modify the codebase and execute git commits.
- Sanitization: There is no requirement for the agent to validate or sanitize the nature of the code changes requested through the user input.
Audit Metadata