skills/billpeet/agent-skills/youtrack/Gen Agent Trust Hub

youtrack

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on shell commands via the yt CLI to search, create, update, and comment on YouTrack issues.
  • [EXTERNAL_DOWNLOADS]: Requires the installation of the @billpeet/yt-cli NPM package. This is a vendor-owned resource associated with the skill author.
  • [DATA_EXFILTRATION]: Identifies that sensitive API credentials are saved locally in the ~/.config/yt-cli/config.json file and provides instructions for managing these credentials via environment variables.
  • [PROMPT_INJECTION]: The skill processes external data (issue summaries, descriptions, and comments) from YouTrack, creating a surface for indirect prompt injection.
  • Ingestion points: Data retrieved from YouTrack through commands like yt issue search, yt issue get, and yt issue comments.
  • Boundary markers: No delimiters or warning markers are used when presenting external content to the agent.
  • Capability inventory: The skill can execute various yt CLI commands, including creating and modifying remote issue data.
  • Sanitization: There is no evidence of sanitization or validation of the text content fetched from the YouTrack instance.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 02:10 AM