scope-audit

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow ingests the user-provided scope document text (e.g., pasted/uploaded “scope.txt”) into ScopeAuditor(text, ...) and runs regex scanning on it; if that document contains outsider-authored free text (e.g., a client’s RFP/SOW or email), that text is fed into the agent’s LLM context via the user’s supplied input.

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

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