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
Risk Level
SAFE
Analyzed
May 30, 2026, 01:54 AM