blueprint
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project structure, existing plan files, and memory logs during its research phase to generate engineering plans. This creates an attack surface where malicious instructions embedded in a project's source code or documentation could potentially influence the agent's plan generation or subsequent execution steps.
- Ingestion points: Research phase reads project structure and existing memory files.
- Boundary markers: None explicitly defined in the skill instructions to delimit untrusted project data.
- Capability inventory: The skill utilizes
git,ghCLI, and standard file system operations to execute generated plans. - Sanitization: No explicit sanitization or filtering of external project content is described in the prompt logic.
Audit Metadata