jmb-implement-ticket

Pass

Audited by Gen Agent Trust Hub on Nov 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from external sources (GitHub issues) which could contain malicious instructions designed to influence the agent's behavior during code implementation.
  • Ingestion points: The skill reads ticket content and comments using gh issue view <n> --comments in the 'Context' step.
  • Boundary markers: Absent. The instructions do not specify delimiters or instructions to ignore embedded commands within the ticket data.
  • Capability inventory: The skill has significant capabilities including file system modification (implementing code), executing shell commands, performing git operations (commit, push), and managing GitHub PRs.
  • Sanitization: Absent. The agent is expected to interpret the ticket content directly to define acceptance criteria.
  • [COMMAND_EXECUTION]: The skill executes a local shell script located in a sibling directory to perform PR review status checks.
  • Evidence: bash <this skill's base directory>/../jmb-review-pr/pending-review.sh <pr> in the 'State' step.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 21, 2026, 06:50 PM