github-project-management

Warn

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: MEDIUMREMOTE_CODE_EXECUTIONPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill executes remote code using npx to run claude-flow@alpha and ruv-swarm packages without fixed versions or integrity checks.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection by processing external data from GitHub issues to drive automated actions. 1. Ingestion points: Data is ingested via gh issue view, gh issue list, and gh project item-list commands in SKILL.md. 2. Boundary markers: None identified. Issue content is processed without clear delimitation. 3. Capability inventory: Includes GitHub CLI operations (gh issue create/edit), project board management, and remote code execution via npx. 4. Sanitization: No sanitization or validation of the fetched issue content is performed before processing.
  • [COMMAND_EXECUTION]: The skill relies on complex shell pipelines involving the GitHub CLI (gh), jq, and npx to automate task decomposition, triage, and board synchronization.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 2, 2026, 07:18 AM
Security Audit — agent-trust-hub — github-project-management