skills/ruvnet/ruflo/federation-init/Gen Agent Trust Hub

federation-init

Warn

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches the '@claude-flow/plugin-agent-federation' package from the public npm registry using the npx tool.
  • [REMOTE_CODE_EXECUTION]: Executing code directly from a remote registry using npx with the @latest tag constitutes remote code execution. This practice is vulnerable to supply chain attacks if the package or registry is compromised.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to run commands that initialize the node and set compliance configurations.
  • [PROMPT_INJECTION]: The MODE variable derived from user input is directly interpolated into a shell command (npx ... --compliance MODE) without sanitization or boundary markers, allowing for potential command injection.
  • Ingestion points: User-supplied compliance mode argument in SKILL.md
  • Boundary markers: None
  • Capability inventory: Bash (npx)
  • Sanitization: None
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 17, 2026, 06:09 PM
Security Audit — agent-trust-hub — federation-init