adr
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed to help maintain documentation for architectural decisions. It operates by reading local project artifacts and writing Markdown files for ADRs.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the project repository to generate architectural records, which presents a standard surface for indirect prompt injection.
- Ingestion points: The agent reads project code, tests, documentation, and version history (SKILL.md).
- Boundary markers: There are no explicit instructions to use delimiters or ignore instructions found within the processed files.
- Capability inventory: The skill utilizes file-system read capabilities to analyze the project and file-system write capabilities to create or update ADR files.
- Sanitization: The instructions do not mandate specific sanitization or validation of the content gathered from project files before inclusion in the ADR.
Audit Metadata