gentle-ai-branch-pr

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard command-line utilities and repository-local scripts to manage development tasks.
  • Orchestrates GitHub interactions via the gh CLI for viewing issues (gh issue view) and creating pull requests (gh pr create).
  • Runs local verification scripts within the repository: go run ./internal/gofmtcheck and ./docker-test.sh.
  • Executes standard version control operations using git.
  • [INDIRECT_PROMPT_INJECTION]: The workflow involves ingesting data from external sources that could potentially contain malicious instructions.
  • Ingestion points: Data enters the context from GitHub issue content via gh issue view and user-provided inputs for pull request summaries.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within external issue data.
  • Capability inventory: The agent is granted capabilities to perform network operations (gh), file system mutations (git), and local code execution (go, docker).
  • Sanitization: There are no explicit sanitization steps for data retrieved from issues before it is used to generate pull request content or commit messages.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 01:46 AM
Security Audit — agent-trust-hub — gentle-ai-branch-pr