power-automate-documentation

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Data Processing Surface: The skill is designed to ingest and analyze Power Automate solution files (.json, .xml). This represents an ingestion surface for external data, which is necessary for its primary documentation purpose.
  • Ingestion points: Workflow definitions and solution metadata are extracted from user-provided solution archives as described in the Solution Zip Anatomy section of SKILL.md.
  • Capability inventory: Across all instructions and scripts, the skill's capabilities are restricted to generating Markdown documentation. It does not utilize or request tools for network access, arbitrary file system writes, or shell command execution.
  • Boundary markers and Sanitization: The instructions emphasize that the 'source of truth' must be the workflow JSON rather than display names or external assumptions. A mandatory 'reconciliation check' requires the agent to verify that every inventoried action is accounted for in the final output, providing a structural safeguard against data manipulation or omission within the processed files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 11:56 PM
Security Audit — agent-trust-hub — power-automate-documentation