khe-svg
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute local Node.js scripts (
scripts/svg-check.mjsandscripts/svg-flipbook.mjs) and the well-knownsvgoutility vianpx. These tools are used for linting and processing SVG files within the workflow. - [INDIRECT_PROMPT_INJECTION]: The skill has a theoretical attack surface for indirect prompt injection as it ingests untrusted data from
.svg,.html,.jsx, and.tsxfiles. - Ingestion points: The agent reads and processes user-provided SVG and markup files during refactoring and linting steps.
- Boundary markers: Absent. There are no explicit instructions to ignore or delimit embedded natural language instructions within the processed data.
- Capability inventory: The agent has capabilities to read/write files and execute local scripts.
- Sanitization: The provided
svg-check.mjsscript validates the structural integrity and attribute safety of the SVG but does not filter for malicious natural language prompts.
Audit Metadata