competitor-tracking

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt includes a sample automation script that sets an API key variable (KEY="apk_your_key") and uses it in curl headers, which encourages embedding secrets into commands/scripts that an agent might be asked to fill or output verbatim, creating exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch public app metadata, keywords, and user reviews via Appeeky API endpoints (e.g., GET /v1/apps/:id, GET /v1/apps/:id/reviews, GET /v1/apps/:id/keywords and market endpoints), which are untrusted third‑party/user‑generated content that the agent must read and that directly drive decisions and follow‑up actions.