ios-redteam-pipeline

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill is an openly advertised offensive iOS testing guide with no concealment, pretext, impersonation, or covert triggers, but it tells the agent to fetch and run an unnamed community Frida script without any vetting, which is a careless supply-chain risk rather than deliberate intent against the user.

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

• Third-party content exposure detected (low risk: 0.10). The required Stage 0 workflow runs the iTunes search and lookup APIs, which return public App Store listings (including releaseNotes) authored by arbitrary developers, so the agent must actively query for outsider-authored marketplace text, which is a low-risk exposure rather than a monitored queue.