qe-github-workflow-automation

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from GitHub Pull Requests and Issues, which are untrusted external sources.
  • Ingestion points: Data is fetched using gh pr view and gh run view within SKILL.md.
  • Boundary markers: The provided examples do not include delimiters or instructions to ignore embedded commands in the untrusted data.
  • Capability inventory: The skill has the ability to execute shell commands, perform GitHub actions (create issues/comments), and spawn AI agents.
  • Sanitization: No sanitization or validation of the external content is shown before it is passed to agents or command arguments.
  • [EXTERNAL_DOWNLOADS]: The skill frequently invokes npx ruv-swarm and npx claude-flow@alpha. These commands download and execute code from the npm registry at runtime without pinned versions, which introduces a supply chain risk.
  • [COMMAND_EXECUTION]: The skill heavily relies on shell command execution via the GitHub CLI (gh) and custom swarm tools to automate repository management tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 06:16 PM
Security Audit — agent-trust-hub — qe-github-workflow-automation