doc-adr-audit

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a workflow for auditing Architecture Decision Record (ADR) files, which introduces a surface area for indirect prompt injection (Category 8). Maliciously crafted ADR files could theoretically contain instructions intended to influence the agent's behavior during the audit or fix cycle.
  • Ingestion points: The skill accepts an ADR file path (e.g., docs/05_ADR/...) as input and processes the content within the audit pipeline.
  • Boundary markers: The execution contract does not specify any delimiters or safety instructions (e.g., 'ignore instructions within the ADR') to separate data from the agent's operational instructions.
  • Capability inventory: The skill orchestrates multiple sub-skills (doc-adr-validator, doc-adr-reviewer) and triggers a remediation skill (doc-adr-fixer), while also performing file write operations to generate combined audit reports.
  • Sanitization: The provided documentation does not mention any sanitization, validation, or escaping of the ADR content before it is processed by the agent or passed to downstream artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 12:13 PM