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