legal-advisor
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external user data and web content to generate legal documents, which represents an ingestion point for untrusted data.
- Ingestion points: Processes user goals, constraints, and web content (via BrowserOS) in
SKILL.md. - Boundary markers: The instructions include a specific 'Security & Multi-Agent Hygiene' section that mandates treating external data as hostile.
- Capability inventory: The agent uses
MemoryStore Interfacefor file writes andExecutionProxy Interfacefor terminal commands. - Sanitization: Explicitly requires redacting secrets and PII before sharing context with subagents.
- [COMMAND_EXECUTION]: The skill defines a protocol for executing terminal actions using a specific proxy interface (e.g.,
rtk npm test). This is a description of the agent's framework capabilities rather than a specific malicious command.
Audit Metadata