cover-image

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can be ingested when the operating user provides “Direct content input” (pasted content) or an external article file; Step 1 “Analyze content” and Step 3 “Create Prompt” then incorporate that text into prompts/cover.md, which is later sent to the image-generation skill/LLM.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)