adr-verbatim
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted user input and write it directly to the file system as an ADR. While this creates an attack surface for indirect prompt injection if other agents later process these records, this is the intended functionality of a verbatim recording tool.
- Ingestion points: User input as specified in SKILL.md.
- Boundary markers: None used in the ADR template, as the output must be verbatim.
- Capability inventory: File system write access to the 'docs/adr/' directory.
- Sanitization: No sanitization is performed, which is consistent with the skill's stated 'verbatim' requirement.
Audit Metadata