plan-feature-from-youtrack

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands via the yt CLI using a user-supplied <card-id> (e.g., yt issues show <card-id>). While the intended usage involves alphanumeric issue IDs, a lack of explicit validation on the identifier string could potentially allow for command injection if the agent environment does not properly escape the input.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes external data that could contain malicious instructions.
  • Ingestion points: Ingests issue descriptions, comments, and metadata from YouTrack via the yt CLI tool in Step 2.
  • Boundary markers: Absent. The skill does not define specific delimiters or instructions for the agent to ignore potentially malicious embedded content within the fetched YouTrack data.
  • Capability inventory: The skill has the ability to execute shell commands (yt) and write Markdown files to the local working directory.
  • Sanitization: Absent. There is no mention of sanitizing or validating the text content retrieved from YouTrack before it is used to ground the generation of specs and plans.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 10:16 PM