gemini-hardened

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses Homebrew to install the gemini-cli utility, which is a well-known and trusted package management service.
  • [COMMAND_EXECUTION]: The skill facilitates the execution of the gemini CLI. It incorporates instructional guardrails requiring explicit user confirmation before the agent performs system-modifying actions or installs extensions.
  • [PROMPT_INJECTION]: The skill processes user-supplied prompts which creates a surface for indirect prompt injection.
  • Ingestion points: Positional arguments in gemini command calls (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: System state modification and extension execution via the CLI tool.
  • Sanitization: Absent; the skill relies on manual user oversight and review as defined in its security guardrails.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 06:31 PM
Security Audit — agent-trust-hub — gemini-hardened