skills/steipete/openclaw/peekaboo/Gen Agent Trust Hub

peekaboo

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the peekaboo CLI tool via Homebrew from the author's official repository (steipete/tap/peekaboo). This is the intended distribution method for the tool.
  • [COMMAND_EXECUTION]: The skill performs its functions by executing the peekaboo binary with various arguments to interact with the macOS accessibility and screen recording APIs.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the user's screen which could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: UI metadata and screen captures enter the context through peekaboo see, peekaboo image, and peekaboo capture commands.
  • Boundary markers: None identified in the skill instructions.
  • Capability inventory: The agent has the ability to click, type, and manage applications via the peekaboo toolset.
  • Sanitization: No explicit sanitization of UI labels or accessibility text is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 02:10 PM
Security Audit — agent-trust-hub — peekaboo