c-screen
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes external CLI tools
peekabooandcamsnapto perform sensitive operations like screen recording and camera capture. These tools interact with system-level APIs and require explicit OS permissions. - [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection via its OCR functionality.
- Ingestion points: Arbitrary text extracted from the screen using
peekaboo ocr. - Boundary markers: None; the skill does not provide markers or instructions to help the agent distinguish between data and commands within the OCR output.
- Capability inventory: The agent can execute shell commands and read local files created by the capture tools.
- Sanitization: No sanitization or validation of the extracted text is performed before it is processed by the agent.
Audit Metadata