dynamics-365

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and run @useclawlink/cli from the NPM registry. This is the official command-line interface provided by the skill's vendor (ClawLink) for managing app connections.
  • [COMMAND_EXECUTION]: The skill operates by executing shell commands to interact with the ClawLink service. It includes specific commands for authentication and running Dynamics 365 actions. It also manages its own session state in a local directory (~/.clawlink/credentials.json).
  • [PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection as it retrieves data from external Dynamics 365 records.
  • Ingestion points: Data returned from actions like get_all_leads or run dynamics-365.
  • Boundary markers: No specific delimiters or "ignore" instructions are used in the command output integration.
  • Capability inventory: The skill can execute shell commands via npx and perform file writes to its configuration path.
  • Sanitization: The instructions mitigate this risk by requiring the agent to "confirm with the user before any write" operation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:42 PM
Security Audit — agent-trust-hub — dynamics-365