copilot-studio-agent-test

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [Command Execution]: The skill instructions frequently use the node command to execute a local JavaScript file (scripts/cs-agent-test.cjs). This is the intended primary function of the skill to perform agent testing, using a self-contained script to avoid external package installation dependencies.
  • [Indirect Prompt Injection Surface]: The skill processes user-supplied data, such as Word documents or CSV files, which are then used as inputs to the agent under test. While this creates a surface for indirect prompt injection (where instructions hidden in the test data might influence the agent's behavior), the skill includes manual grading steps (PASS/FAIL/EXCLUDED) and human review of the results, which serves as a mitigation for this type of risk.
  • [Data Handling]: The skill stores configuration and authentication tokens in the user's home directory (~/.cs-agent-test/) rather than the skill folder itself. This is a security best practice to ensure that sensitive environment details are not accidentally shared if the skill folder is version-controlled.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 11:55 PM
Security Audit — agent-trust-hub — copilot-studio-agent-test