blueprint
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its architecture as a plan generator.
- Ingestion points: The skill ingests untrusted data from user-provided objectives and existing project structure/memory files during the 'Research' phase (SKILL.md).
- Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when processing external input to ensure it is not interpreted as part of the plan logic.
- Capability inventory: The skill possesses the capability to write files (creating markdown plans in the
plans/directory), read project files, and interact with the Git and GitHub CLI toolsets. - Sanitization: The instructions do not define sanitization, validation, or escaping protocols for user-provided objectives before they are interpolated into the generated construction plans.
Audit Metadata