adr-critique
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface as it processes untrusted content from architectural documentation.
- Ingestion points: The skill reads local ADR files and globs LikeC4 configuration and model files (**/*.c4).
- Boundary markers: Absent; the skill does not utilize specific delimiters or instructions to isolate ingested documentation content from agent instructions.
- Capability inventory: The skill possesses read access to local project files and write access to modify ADR documentation.
- Sanitization: No sanitization or validation is applied to the ingested content before it is processed by the agent.
Audit Metadata