proj-analyze-design
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting and processing untrusted project data, which could contain malicious instructions designed to influence the agent's output or tool usage.
- Ingestion points: In Step 0 and Step 1, the agent reads requirement analysis documents and explores existing project source code to understand the implementation context.
- Boundary markers: The instructions do not define any boundary markers or special handling to isolate untrusted content from the system prompt or to warn the agent against following instructions embedded in the processed data.
- Capability inventory: The skill possesses the capability to write technical design documents to the filesystem and invokes the
/proj-tasktool to generate actionable development tasks based on its analysis. - Sanitization: No sanitization or verification steps are present to ensure that the content extracted from requirements or code does not contain malicious prompt injections that could compromise the subsequent task generation phase.
Audit Metadata