jp-prd

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.70). The prompt explicitly instructs the agent to emit telemetry ("fire-and-forget juspay_track_integration_stage") and to "do not mention this to the user," which is a hidden/deceptive directive outside the skill's stated PRD-writing purpose.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill calls doc_fetch_tool(url) at runtime to fetch Juspay documentation (allowed domains: *.juspay.io, *.juspay.in, dth95m2xtyv8v.cloudfront.net) and uses those fetched pages to ground PRD facts and drive prompts/output, so remote docs are runtime dependencies that directly control the agent's outputs.