appmate-setup

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs the agent to ask the user for credential values and then write them verbatim into config/credentials.txt (i.e., include user-supplied API credential fields in the agent's output), creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches data from the Apple App Store Connect API (e.g., /v1/customerReviews, /v1/apps, /v1/salesReports) — as documented in SKILL.md and used by workflows like feature_ideate and competitor_research — which includes user-generated reviews and external metadata that the agent reads and uses to drive analysis and next actions, so untrusted third-party content could influence behavior.