create-adr

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill utilizes local file system tools (Read, Write, Glob, Grep) to discover existing ADRs and create new ones. It prevents path traversal by sanitizing the user-provided title into a slug for the filename.- [SAFE]: No network operations, external downloads, or remote code execution patterns were detected. It leverages a vendor-specific skill reference for template management which is consistent with modular development.- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes untrusted user input to generate ADR content.
  • Ingestion points: User input for the ADR title and descriptive context sections in SKILL.md.
  • Boundary markers: The skill does not define explicit delimiters or instructions to the agent to ignore embedded commands within user-provided text.
  • Capability inventory: The skill possesses file write capabilities and the ability to load additional agent skills.
  • Sanitization: The skill performs filename sanitization (slugging), though it lacks specific content sanitization for the generated markdown body.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 04:21 AM