architecture-lens
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze external codebases and design documents, which creates a theoretical surface for indirect prompt injection if the analyzed content contains malicious instructions.
- Ingestion points: Code files, architectural contracts, and design evidence within the repository being reviewed (as specified in
SKILL.md). - Boundary markers: The skill does not explicitly define delimiters to separate its core instructions from the code content it processes.
- Capability inventory: The skill is primarily read-only (reporting findings), but it acknowledges the ability to perform 'scoped fixes' (file writes) if specifically authorized by a user request (
SKILL.md). - Sanitization: There are no specific sanitization or filtering steps mentioned for the external content being analyzed.
Audit Metadata