linkfox-jiimore-page-asins-by-asin

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow for this skill calls a backend endpoint (POST /jiimore/pageAsinsByAsin) with user-supplied JSON and then ingests the returned JSON fields (including product titles/brands/niche titles/links) to print/save results, so outsider-authored free text can reach the agent via the API response without needing pre-selection.

HIGH W008: Secret detected in skill content (API keys, tokens, passwords).

• Secret detected (high risk: 1.00). I scanned the skill files for literal, high-entropy values that could provide access. The only candidate is the base64-like string assigned to _LOGIN_FIXED_UID in scripts/onboarding.py. It's a hardcoded, non-placeholder, high-entropy string used as a fixed UID header for the login flow ("登录链路固定 uid header（实测可用）"), which can be used in requests and therefore may grant or facilitate access. No other API keys, PEM blocks, or similarly high-entropy credentials are present. (Other values are environment variable names, examples, or short/non-secret literals and were ignored.)