setup-skills

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill automates the creation of documentation files and the update of project-specific agent instructions. The operations are limited to reading repository metadata and writing configuration files to the local file system within the docs/ and .scratch/ directories.
  • [COMMAND_EXECUTION]: Provides instructions for using the GitHub CLI (gh) and GitLab CLI (glab) to manage issues and pull requests. These are official, well-known developer tools, and their use is restricted to standard project management operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from repository files such as .git/config, CLAUDE.md, and AGENTS.md to understand the current project state. While this represents a data ingestion surface, the skill implements safety by summarizing findings and requiring explicit user confirmation before any modifications are committed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 11:35 AM
Security Audit — agent-trust-hub — setup-skills