warp-deploy-register-route

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

• Third-party content exposure detected (high risk: 0.75). The skill may fetch outsider-authored Linear ticket URLs at runtime (public/third-party issue content) and then uses the extracted free-text fields (e.g., “Route Type”, “Connected Chains”, ownership/ICA notes) to drive subsequent config generation, which can be ingested into the agent/LLM context via the ticket text.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)