advogado-especialista-v2

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill documentation includes examples of command-line usage for an external orchestrator framework (e.g., python agent-orchestrator/scripts/match_skills.py). These are presented as usage instructions and are not executed automatically.
  • [DATA_EXPOSURE]: The skill contains a hardcoded local Windows file path in the documentation (C:\Users\renat\skills\agent-orchestrator\scripts\scan_registry.py). While this exposes a local username ('renat'), it is an informational artifact from the skill's original development environment and does not constitute a high-risk data leak.
  • [EXTERNAL_DOWNLOADS]: The skill references a public GitHub repository (https://github.com/sickn33/antigravity-awesome-skills) as its source of origin. This is documented transparently in ORIGIN.md and metadata.json as part of the provenance trail for imported content.
  • [INDIRECT_PROMPT_INJECTION]: As a legal knowledge base, the skill processes user queries about legal cases. It includes specific safety guidelines ('Restricoes Absolutas') for the agent, such as not inventing laws or minimizing domestic violence, which serve as defensive instructions against potential misuse.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 05:49 PM
Security Audit — agent-trust-hub — advogado-especialista-v2