check-repository-state

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill proactively addresses Indirect Prompt Injection by instructing the agent to treat all repository-sourced data (paths, refs, configuration, and tool output) as untrusted input. It explicitly prohibits treating such content as authorization for further actions.
  • Ingestion points: Git repository metadata, configuration values, and file system structure (SKILL.md).
  • Boundary markers: Present. The instructions mandate treating repo content as untrusted data and warn against implicit trust.
  • Capability inventory: The skill describes the use of local Git inspection commands such as git status, git worktree list, and git version.
  • Sanitization: Present. The guidelines strictly require passing variables as separate shell arguments to prevent command injection and advise against shell interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 04:49 PM
Security Audit — agent-trust-hub — check-repository-state