Skills
skills/yusuke-suzuki/dotfiles/publish/Gen Agent Trust Hub

publish

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses git and gh (GitHub CLI) to perform standard development operations, including pushing code and updating pull request metadata.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection because it incorporates external content from the repository into its operational logic.
  • Ingestion points: The skill reads pull request templates from the local file system (**/pull_request_template.md) and existing PR descriptions via gh pr view (SKILL.md).
  • Boundary markers: None identified. The skill instructions do not specify delimiters to isolate content from these sources.
  • Capability inventory: The skill has permissions to push to remote branches (git push) and modify pull request content (gh pr edit) (SKILL.md).
  • Sanitization: No sanitization or verification of the external content is performed before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 01:33 AM