skills/joacod/skills/ticket-to-pr/Gen Agent Trust Hub

ticket-to-pr

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform repository management tasks using the GitHub CLI (gh) and standard Git commands. These actions include creating branches, making commits, pushing code to remote repositories, and opening pull requests. While these are intended functions, they represent the capability to execute powerful shell commands that interact with external services.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon external "ticket" data provided as arguments during invocation, which constitutes a potential injection surface.
  • Ingestion points: Ticket content passed as arguments to the ticket-to-pr command in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the ticket text.
  • Capability inventory: The agent is granted the ability to modify project files, create and push Git branches, and generate Pull Requests on GitHub using gh.
  • Sanitization: There are no documented steps for validating, filtering, or escaping the contents of the ticket before the agent uses it to guide implementation or pull request description generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 04:50 AM
Security Audit — agent-trust-hub — ticket-to-pr