helix-mcp-icp-intelligence
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, unauthorized command execution, or deceptive obfuscation techniques were detected. The skill's instructions prioritize accuracy and user verification.
- [EXTERNAL_DOWNLOADS]: The skill references a hosted MCP endpoint (https://icp-intelligence.gtmhelix.com/mcp) and an NPM package (@shashwatgtmalpha/icp-intelligence-mcp). These resources are owned by the author (shashwatgtm/Helix GTM Consulting) and are used to provide the core functionality of the skill.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data such as customer interview notes and account lists (identified in SKILL.md). While this represents an attack surface, it is mitigated by the 'Operating Principles' (Rule 2 and Rule 4), which require the agent to verify all factual claims via web search or direct user confirmation before including them in any final deliverable.
Audit Metadata