pencil
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external
.pendesign files which may contain untrusted instructions. - Ingestion points:
batch_getandget_editor_statein SKILL.md. - Boundary markers: The skill instructs the agent to use tool-based access rather than raw reading, but lacks explicit ignore-instruction delimiters for content.
- Capability inventory:
batch_design(file modification),set_variables, andget_screenshot. - Sanitization: No sanitization or validation of the design file content is specified.
- [COMMAND_EXECUTION]: The
batch_designtool interprets and executes anoperationsscript string. While restricted to the Pencil design domain, this represents a dynamic execution vector if user input is interpolated. - [CREDENTIALS_UNSAFE]: The MCP server configuration example in SKILL.md includes an absolute file path (
/Users/wandl/...) that exposes a local system username.
Audit Metadata