Skills
skills/moonshotai/kimi-cli/pull-request/Gen Agent Trust Hub

pull-request

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the gh (GitHub CLI) utility to perform git push operations and submit pull requests to GitHub repositories.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface as it ingests untrusted code diffs to generate PR titles and descriptions. 1. Ingestion points: branch diffs relative to the main branch. 2. Boundary markers: none identified in the workflow logic. 3. Capability inventory: push and PR creation via gh CLI. 4. Sanitization: none performed on input diffs before processing for natural language generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 10:27 AM
Security Audit — agent-trust-hub — pull-request