skills/ryoppippi/ccusage/create-pr/Gen Agent Trust Hub

create-pr

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of local command-line tools including git and gh to perform repository operations such as creating branches, staging changes, and pushing code.
  • [DATA_EXFILTRATION]: Network communication is initiated through git and gh to interact with GitHub's servers for pushing code and managing Pull Request metadata (comments, reviews, and status checks). These operations are well-defined and align with the skill's primary purpose of PR management.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it polls and processes external data from GitHub PR comments and reviews (e.g., in references/ai-review.md and references/gh-review.md). This data is then used to inform subsequent agent actions. While there are no explicit boundary markers or sanitization steps mentioned for this ingested content, the behavior is within the expected scope for a pull request automation tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 07:21 AM
Security Audit — agent-trust-hub — create-pr