legaltech-expert
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified in the skill instructions or reference code. The content is professional, domain-specific, and uses standard libraries.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze external legal documents (contracts, e-discovery files), which is an inherent ingestion surface for potentially untrusted data.
- Ingestion points: Document text and metadata are ingested for parsing and risk analysis in
references/EXAMPLES.md. - Boundary markers: The instructions do not specify the use of delimiters or provide the agent with explicit instructions to ignore commands that may be embedded within documents.
- Capability inventory: The skill is configured with
Bash,Read,Write, andWebSearchtools, providing a broad capability set. - Sanitization: The implementation uses regular expressions for feature extraction but does not include specific logic to sanitize or filter potential instructions found in the document text.
Audit Metadata