security-usernames

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

• Third-party content exposure detected (high risk: 0.85). The skill ingests outsider-authored free text at runtime by reading bundled reference files (e.g., references/Usernames/cirt-default-usernames.txt and top-usernames-shortlist.txt) that originate from the public SecLists GitHub repository, which are then loaded as readable lines into the agent’s context for username enumeration.

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

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