peekaboo
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local binary
peekabooto perform high-privilege GUI automation tasks. This includes listing active applications and windows, simulating mouse clicks, and performing text entry. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from the operating system's UI elements.
- Ingestion points: UI element labels and screen content retrieved via
see --json --annotateandimagecommands (SKILL.md). - Boundary markers: The instructions do not define clear boundaries or delimiters to differentiate between the agent's instructions and the content being read from the screen.
- Capability inventory: The tool possesses the ability to perform shell-based GUI manipulation (
click,type) and file system access for saving screenshots (SKILL.md). - Sanitization: There is no evidence of sanitization or validation of the UI text before it is processed by the agent.
Audit Metadata