intel-overdrive

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the global installation of an NPM package (intel-overdrive) that originates from an unverified third-party source rather than a trusted organization or well-known service.
  • [COMMAND_EXECUTION]: The setup instructions involve running shell commands to install and configure the MCP server (npm install -g intel-overdrive && intel-overdrive setup), which executes code at the user's privilege level.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it aggregates and processes data from over 1100 external, potentially untrusted sources through the overdrive_intel tool.
  • Ingestion points: Data fetched via the overdrive_intel tool from external sources like package registries and marketplaces (SKILL.md).
  • Boundary markers: Absent; the instructions do not define delimiters or provide warnings for the agent to ignore instructions embedded in the tool output.
  • Capability inventory: The skill is intended for use with powerful agents like Claude Code and Cursor, which often possess file system access and shell execution capabilities.
  • Sanitization: There is no mention of content filtering, escaping, or validation of the fetched intelligence data before it is integrated into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 01:31 PM