github-release-management

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of system commands through the Bash() function and GitHub CLI (gh) to perform actions such as creating releases, managing branches, and handling deployments.
  • [EXTERNAL_DOWNLOADS]: It leverages npx to dynamically fetch and execute the claude-flow toolset and other related packages. These resources are associated with the skill's author and represent intended orchestration functionality.
  • [PROMPT_INJECTION]: The skill ingests commit messages and pull request titles from repository history to generate automated changelogs. This ingestion of untrusted data into an AI-driven process constitutes an indirect prompt injection surface.
  • Ingestion points: Data enters via GitHub API queries for commit messages and PR metadata (e.g., gh api repos/:owner/:repo$compare/...).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the snippets that pass this data to the changelog generator.
  • Capability inventory: The skill has the ability to execute shell commands (Bash), write files (Write), and execute node packages (npx).
  • Sanitization: There is no evidence of filtering or sanitization of the commit/PR text before it is processed by the AI orchestration tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 04:33 PM