font-measurement
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill utilizes the $ARGUMENTS placeholder to ingest user-supplied tasks directly into the agent's context without employing boundary markers (such as XML tags or specific delimiters) or instructions to disregard embedded commands. This configuration creates a vulnerability surface for indirect prompt injection, particularly as the skill environment is configured with high-privilege tools.
- Ingestion points: The $ARGUMENTS variable within SKILL.md.
- Boundary markers: Absent around the input variable.
- Capability inventory: The skill has access to Bash, Write, Edit, Read, Grep, and Glob tools.
- Sanitization: No validation or sanitization logic is specified for the ingested content.
- [EXTERNAL_DOWNLOADS]: The documentation references the installation of the @evenrealities/pretext Node.js package. This resource is provided by the skill's authoring organization and is used for layout dimension calculations.
Audit Metadata