pencil-mcp-get-editor-state
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access mechanisms were detected.
- [PROMPT_INJECTION]: No evidence of attempts to override agent behavior or bypass safety filters. The skill contains instructional constraints that reinforce intended use and prevent accidental tool invocation.
- [DATA_EXFILTRATION]: The skill interacts with an environment state tool that returns internal metadata such as current selection IDs and document file paths. This data is scoped to the design application context and no external network transmission patterns were identified.
- [COMMAND_EXECUTION]: No arbitrary command execution, shell spawning, or script generation patterns were found.
- [REMOTE_CODE_EXECUTION]: The skill does not perform any remote downloads or execute external scripts.
Audit Metadata