skills/yamadashy/skills/only-you/Gen Agent Trust Hub

only-you

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists of high-level reasoning instructions and strategic guidelines. It does not include executable scripts, hardcoded credentials, or external network dependencies.
  • [COMMAND_EXECUTION]: The instructions direct the agent to use 'git log' to analyze the history and values of a repository. This is a standard, low-risk operation intended for project context gathering.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to its core function of analyzing untrusted repository data.
  • Ingestion points: The skill instructs the agent to read repository files and git history (SKILL.md).
  • Boundary markers: No specific delimiters or isolation instructions are used to distinguish between repository content and the agent's internal instructions.
  • Capability inventory: The skill uses 'git log' for reconnaissance and is designed to lead into task execution once user permission is granted.
  • Sanitization: There are no explicit steps provided for sanitizing or validating the content retrieved from the repository files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 04:47 AM
Security Audit — agent-trust-hub — only-you