clippy
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
pbcopyandpbpasteon macOS to handle clipboard operations when requested by the user. - [INDIRECT_PROMPT_INJECTION]: The skill processes conversation state and notes to create checkpoints, which presents an attack surface for instructions embedded in the conversation history.
- Ingestion points: Processes conversation history, delayed messages, and existing coordination notes as described in SKILL.md.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified for the reconciliation process.
- Capability inventory: Executes shell commands (
pbcopy,pbpaste) and updates persistent checkpoint notes. - Sanitization: No specific evidence of output escaping or input validation is provided for the content being preserved.
- [SAFE]: References to the OpenAI Codex repository on GitHub point to a well-known and trusted organization's official resources.
Audit Metadata