architect
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it analyzes external source code subsystems to ground its architectural designs.\n
- Ingestion points: SKILL.md (Phase A) specifies building a mental model by running analysis tools over existing code subsystems.\n
- Boundary markers: The instructions do not define specific delimiters or guidelines to ignore potential instructions embedded within the analyzed source code.\n
- Capability inventory: SKILL.md (Phase D) authorizes the agent to replace placeholders with actual implementation logic and write code to the project files.\n
- Sanitization: No explicit sanitization or filtering of the ingested code content is described before it influences the architectural sketch.
Audit Metadata