adr-management

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection vulnerability surface because it processes content within ADR files that could potentially contain malicious instructions.\n
  • Ingestion points: scripts/adr_manager.py reads the contents of existing markdown files from the ADRs/ directory during search and retrieval operations.\n
  • Boundary markers: The skill does not utilize specific delimiters or instructions to treat embedded content in ADR files as non-executable data, potentially allowing embedded instructions to be interpreted by the agent.\n
  • Capability inventory: The skill possesses file-writing capabilities via scripts/adr_manager.py, which are used to scaffold and update ADR markdown files.\n
  • Sanitization: User-provided input is directly interpolated into ADR templates without sanitization to prevent the injection of instructions or markdown-based control characters.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 06:51 PM