skills/microsoft/fluentui/change/Gen Agent Trust Hub

change

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [Command Execution]: The skill utilizes the Bash tool to run yarn commands defined within the local repository's package.json. This is a standard method for interacting with project-specific development scripts and is aligned with the vendor's ecosystem.
  • [Indirect Prompt Injection]: The skill is designed to read and interpret file changes (diffs) to generate descriptive change messages. Because these diffs originate from external sources (the code being changed), they could potentially contain instructions that influence the agent's behavior.
  • Ingestion points: File modifications and git diffs accessed via Bash, Read, Grep, and Glob tools as part of the SKILL.md workflow.
  • Boundary markers: No explicit delimiters are specified in the instructions to distinguish between code data and natural language instructions within the diffs.
  • Capability inventory: The skill utilizes the Bash tool, which allows for shell command execution within the agent environment.
  • Sanitization: There is no evidence of specific input sanitization or filtering applied to the diff data before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 05:42 PM
Security Audit — agent-trust-hub — change