architect
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it ingests untrusted data from the user and the local codebase to guide the behavior of sub-agents.
- Ingestion points: User-provided design tasks and grounding artifacts extracted from existing subsystems (SKILL.md, Phase A and B).
- Boundary markers: The skill does not implement explicit delimiters or instructions to ignore malicious content potentially embedded in the source code or requirements it analyzes.
- Capability inventory: The skill's primary function is generating documentation, type sketches, and signatures. It does not have capabilities for direct shell execution, network exfiltration, or privileged file system modifications.
- Sanitization: There is no evidence of input validation or sanitization before the grounding artifacts are interpolated into the prompt templates for the sub-agents (runners).
Audit Metadata