recon-mattress-stores

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly instructs fetching page/JS content and grepping for API/public_key patterns (and cites real examples of exposed API keys), which encourages extracting and outputting secret API keys verbatim if findings are reported.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document is explicit malicious reconnaissance and exploitation guidance for e-commerce sites (data exfiltration, API key harvesting, coupon brute-forcing, and checkout/financing manipulation) and therefore poses high intentional abuse risk.

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md’s required runtime workflow uses curl to fetch outsider-authored free text/JSON from arbitrary target web pages and APIs (e.g., /store-locator, /api/stores, /api/locations, /products.json, /wp-json/wc/v3/*), which is then parsed/printed via jq/grep and thus can be ingested into the agent’s LLM context.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The skill explicitly targets e-commerce financing/payment integrations and names specific payment/financing providers (Affirm, Klarna, Bread) and their APIs. It includes commands to discover payment/financing JS/libs and to locate API keys and pre-qualification endpoints, and mentions checkout bypass/price manipulation and POST endpoints for cart/discount updates. These are specific financial/payment APIs and actions (not generic tooling), so the skill grants direct financial execution capability via payment/financing APIs.