System Architect
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [No Code] (SAFE): The skill consists entirely of markdown instructions for the AI agent and does not contain any executable scripts, binaries, or automated command-line hooks.\n- [Indirect Prompt Injection] (SAFE): The skill processes project documentation (PRDs and tech specs) to generate architectural designs. While this constitutes an ingestion surface for untrusted data, the risk is negligible as it is necessary for the skill's primary function and involves no high-risk capabilities.\n
- Ingestion points: Reads from
docs/prd-*.mdanddocs/tech-spec-*.md.\n - Boundary markers: Delimiters for external content are not explicitly defined within this file.\n
- Capability inventory: Capability to write architectural documents to the file system and store decisions via a memory tool.\n
- Sanitization: No input sanitization or validation routines are specified in the prompt.
Audit Metadata