gitnexus-impact-analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.65). At runtime the workflow explicitly includes “READ gitnexus://repo/{name}/processes” (and uses gitnexus_impact output), which can ingest free-text process/graph content originating from an external repo/index rather than the operating user’s own authored text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill's workflow explicitly performs a runtime read of an external resource via gitnexus://repo/{name}/processes, which would fetch repo content used to drive the agent's impact analysis and therefore directly influence the agent's prompts/behavior (flagged URL: gitnexus://repo/{name}/processes).