security-passwords

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

• Third-party content exposure detected (high risk: 0.95). Outsider-authored free text is ingested because the skill loads password list .txt files (e.g., references/Passwords/Common-Credentials/10k-most-common.txt) and reads their line-by-line contents into runtime-readable prose for the agent/LLM context.

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

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