clade-data-handling
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, persistence mechanisms, or unauthorized network operations were detected.
- [PROMPT_INJECTION]: The skill defines logic for processing conversation messages and text, which creates a surface for indirect prompt injection.
- Ingestion points: Processes 'messages' and 'text' strings as described in the TypeScript snippets in SKILL.md.
- Boundary markers: No explicit boundary delimiters are present in the code examples to isolate untrusted data.
- Capability inventory: The skill is configured to use 'Read', 'Write', and 'Edit' tools.
- Sanitization: The skill provides regex-based PII redaction for emails, phone numbers, SSNs, and credit cards as a security measure.
Audit Metadata