idp-architect
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided architectural requirements and workflows.
- Ingestion points: Processes architectural task descriptions provided as input to the agent (SKILL.md).
- Boundary markers: None present in the instructions to delimit user input from system prompts.
- Capability inventory: The skill contains no executable scripts, subprocess calls, file-system write operations, or network capabilities.
- Sanitization: No explicit sanitization of input data is performed. However, due to the lack of action-oriented capabilities, the risk of exploitation is negligible.
Audit Metadata