legal-counsel

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill defines operational protocols and security guidelines for the 'Agentic Company Framework'. It establishes mandatory risk assessment procedures and context verification steps to ensure deterministic and safe execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a framework for handling untrusted data. (1) Ingestion points: Web content and external data via BrowserOS (SKILL.md). (2) Boundary markers: Absent. (3) Capability inventory: Terminal execution via the rtk prefix and MCP tool usage including sequentialthinking and context7 (SKILL.md). (4) Sanitization: Mandatory redaction of secrets and PII before sharing context with subagents. These protocols are designed to mitigate risks when processing external inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 07:35 AM
Security Audit — agent-trust-hub — legal-counsel