legal-advisor

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious instructions, obfuscation techniques, or unauthorized data exfiltration patterns were detected in the skill definitions.
  • [NO_CODE]: This skill is entirely composed of markdown instructions and metadata, containing no scripts, binaries, or automated installation steps.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection due to its core function of analyzing external legal documents.
  • Ingestion points: Accesses business models, contracts, and policy documents via a context manager as specified in SKILL.md.
  • Boundary markers: Absent; there are no delimiters or specific instructions to the agent to disregard commands potentially embedded in the documents being reviewed.
  • Capability inventory: The skill has no high-risk capabilities, such as shell command execution, network requests, or file system modifications.
  • Sanitization: There is no mention of input validation or content filtering for the documents it processes.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 05:02 PM