plan-feature-from-youtrack

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute the yt (YouTrack CLI) tool to retrieve issue details, comments, and relationship data. This is limited to data retrieval and is consistent with the skill's primary purpose.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it ingests and processes content from an external source (YouTrack issues) that could theoretically contain malicious instructions.
  • Ingestion points: Data is brought into the agent context via yt issues show, yt issues comments list, and yt issues related commands in SKILL.md (Step 2).
  • Boundary markers: The skill does not explicitly use boundary markers or "ignore instructions" delimiters when processing the fetched YouTrack content.
  • Capability inventory: The agent has the capability to write files to the local system (<card-id>-spec.md, <card-id>-plan.md) and execute shell commands via the yt CLI.
  • Sanitization: There is no evidence of sanitization or filtering of the YouTrack issue description or comments before they are used to generate the spec and plan.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 10:00 PM
Security Audit — agent-trust-hub — plan-feature-from-youtrack