pii-detect
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes arbitrary input text via the
<input-text>argument, creating a surface for indirect prompt injection. While the primary purpose is security-focused (PII detection), malicious instructions embedded in the analyzed text could attempt to influence agent behavior. - Ingestion points: Processed via the
<input-text>argument in SKILL.md. - Boundary markers: None explicitly defined in the provided instructions to delimit the untrusted input.
- Capability inventory: Uses specialized PII detection tools (
mcp__claude-flow__aidefence_*) and has access to the Bash tool for processing. - Sanitization: No explicit sanitization or escaping of the input text is mentioned before it is passed to analysis tools.
Audit Metadata