decision-memory
Pass
Audited by Gen Agent Trust Hub on May 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Evaluated for indirect prompt injection vulnerability due to the processing of untrusted repository data and code diffs.
- Ingestion points: SKILL.md Workflow steps 1 and 3 involve reading repository guidance (README, etc.) and code changes.
- Boundary markers: Absent; the skill does not specify the use of delimiters or instructions to ignore potential commands within the analyzed data.
- Capability inventory: The skill can create and update files in the repository (ADRs) and execute standard git commands (
git diff --check). - Sanitization: No explicit sanitization or validation of input data is mentioned before it is used to generate documentation.
Audit Metadata