write-adr

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: Uses shell commands including git branch, git log, ls, and find to inspect the repository state and track the count of existing documentation files.
  • [COMMAND_EXECUTION]: Executes a local Python script at skills/adr-writing/scripts/next_adr_number.py to calculate the next sequence number for ADR files.
  • [PROMPT_INJECTION]: Ingests and analyzes conversation history to extract architectural decisions (indirect prompt injection surface). The risk is mitigated by the use of structured subagent tasks and JSON output formats to maintain context boundaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 09:29 AM