recon-bakeries

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill is an explicit offensive recon playbook targeting small e-commerce sites, with step-by-step commands to discover and retrieve customer orders, PII, API keys, perform injection tests, and brute-force coupons — facilitating data exfiltration and abuse.

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

• Third-party content exposure detected (high risk: 0.70). The required workflow is runtime HTTP fetching of target web pages/APIs (e.g., curl ... /order-cake, /store-locator, /api/locations) and then grepping/parsing the returned HTML/JSON, which can include outsider-authored free text from the target site into the agent’s LLM context.