intelligence-route

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 the @claude-flow/cli package from the NPM registry at runtime.
  • [REMOTE_CODE_EXECUTION]: Running npx @claude-flow/cli@latest executes remote code downloaded from a public repository without version pinning.
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool and provides shell commands to perform routing and track task success.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes untrusted task descriptions through multiple intelligence and prediction tools.
  • Ingestion points: The <task-description> input in SKILL.md.
  • Boundary markers: None; input is passed directly to tool parameters.
  • Capability inventory: Access to shell commands and network-based routing tools.
  • Sanitization: No input validation or sanitization is mentioned.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 28, 2026, 03:01 PM
Security Audit — agent-trust-hub — intelligence-route