test-gaps
Warn
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and run the @claude-flow/cli package from the public NPM registry at runtime.
- [REMOTE_CODE_EXECUTION]: By invoking npx @claude-flow/cli@latest, the skill executes code from a third-party package source that is not included in the trusted vendor list, posing a risk of executing malicious code if the package is compromised.
- [COMMAND_EXECUTION]: The skill requires Bash permissions to run CLI tools and calls an MCP tool mcp__claude-flow__hooks_worker-dispatch to manage background worker tasks.
- [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by processing local file paths (e.g., --path src/) and user-defined tasks without explicit sanitization or instruction boundaries. 1. Ingestion points: File paths and task descriptions in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Bash execution via npx in SKILL.md. 4. Sanitization: Absent.
Audit Metadata