create-adr
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests user-provided text to create and name architectural decision files.
- Ingestion points: User input gathered for ADR topics, problems, and alternatives in Step 1, which are later written to the file system.
- Boundary markers: The instructions do not define specific delimiters or boundary markers to isolate untrusted user data from the ADR structure or subsequent processing.
- Capability inventory: The skill utilizes the
Writetool to create files andBash(ls) to check the file system state. - Sanitization: Step 3 explicitly instructs the agent to sanitize input by removing path traversal characters (.., /, ), null bytes, and control characters, which mitigates file system manipulation risks.
Audit Metadata