gentle-ai-collab-perfect

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides structured guidance for repository workflow compliance, emphasizing honesty in PR reporting and adherence to maintainer-defined constraints.
  • [COMMAND_EXECUTION]: The skill utilizes standard command-line tools such as git, gh (GitHub CLI), and go for development tasks. These are appropriate for the skill's stated purpose of contributing to a software project.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface as it ingests untrusted data from repository files (e.g., CONTRIBUTING.md) and GitHub API responses (e.g., gh pr view).
  • Ingestion points: Reads local markdown files, YAML templates, and GitHub API output via the gh tool.
  • Boundary markers: None explicitly defined for external content, though it instructs the agent to treat repo files as the "Source of truth."
  • Capability inventory: Can execute shell commands (git, gh, go), which allows for file system and network interaction.
  • Sanitization: None specified for the data read from external sources.
  • [EXTERNAL_DOWNLOADS]: The skill references an official documentation URL from GitHub for workflow approval guidance, which is a well-known and trusted service.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 02:22 AM
Security Audit — agent-trust-hub — gentle-ai-collab-perfect