ie-connect-dots
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill file consists entirely of natural language instructions and structural templates for semantic clustering and pattern recognition. It does not perform any direct system operations or data modifications.
- [NO_CODE]: There are no scripts, binaries, or command-line executions defined in the provided file. It serves as a behavioral guide for an AI agent rather than a technical tool.
- [PROMPT_INJECTION]: While the skill processes untrusted user-provided notes (a potential surface for indirect prompt injection), the skill definition itself lacks the capabilities (such as network access or shell execution) required to manifest a security risk from such data.
- Ingestion points: Processes notes from
ie-retrieve-memoryor direct user input. - Boundary markers: None explicitly defined for the data processing phase.
- Capability inventory: No dangerous tools or commands (e.g., subprocess, network, file write) are requested or used.
- Sanitization: No specific sanitization logic is described for the incoming text data.
Audit Metadata