woostack-ideate
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is composed entirely of documentation and instructional Markdown files. No scripts (e.g., Python, JavaScript, Shell) or binary executables are included.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external inputs such as user goals, specifications, and existing codebase content.
- Ingestion points: The skill accepts a
<goal-or-specification>parameter and reads repository data to explore requirements. - Boundary markers: An explicit 'Read-only boundary' is established in SKILL.md, stating it makes no provider calls and takes no commit/PR actions.
- Capability inventory: The skill is restricted to read-only exploration and does not include tools for system modification or state writing.
- Sanitization: references/patterns.md (Rule 3) instructs the agent to use adapters to validate or narrow untrusted wire input at application boundaries.
Audit Metadata