runtime-bridge-conflict-resolver

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely diagnostic and text-based. It does not contain any instructions or tools for the agent to execute shell commands, perform network operations, or modify the local file system.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface by requesting the ingestion of untrusted configuration data from the operator. Ingestion points: Lists of configured MCP servers and enabled Blender add-ons (SKILL.md). Boundary markers: No explicit delimiters are used for the interpolated configuration data. Capability inventory: The skill explicitly restricts all operational capabilities, including file edits, port changes, and process management (SKILL.md). Sanitization: No validation or sanitization of the user-provided configuration strings is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 07:02 PM