common-architecture-diagramming
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its requirement to process and update user-provided architectural documentation.
- Ingestion points: The skill triggers on and reads content from
ARCHITECTURE.md,**/*.mermaid, and**/*.drawiofiles (SKILL.md). - Boundary markers: There are no instructions or patterns provided to isolate external content or warn the agent to ignore instructions embedded in these files.
- Capability inventory: The skill includes instructions for the agent to modify and update architectural files on the file system.
- Sanitization: The skill does not implement any validation or sanitization of the input data before processing it for diagram generation or documentation updates.
Audit Metadata