release-please-pr-workflow

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes official development tools, specifically the GitHub CLI (gh) and git, to perform repository management operations including listing, viewing, merging, and closing pull requests, as well as triggering GitHub Action workflows.- [INDIRECT_PROMPT_INJECTION]: The provided automation scripts ingest and process data from the GitHub API (PR numbers and merge statuses) to determine subsequent actions. While this constitutes a data processing surface, the risk is minimized as follows:
  • Ingestion points: Data is retrieved directly from the GitHub API via gh pr list and gh pr view output in SKILL.md automation examples.
  • Boundary markers: Not explicitly defined in shell logic, but the workflow relies on structured JSON output from a trusted service.
  • Capability inventory: Scripts have the capability to merge and close pull requests via the shell.
  • Sanitization: Employs jq filtering (via the gh command's -q flag) to isolate specific numeric IDs and predefined status strings before command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 03:59 AM
Security Audit — agent-trust-hub — release-please-pr-workflow