lism-css-guide
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: No malicious patterns or security risks were detected. The skill consists of documentation and procedural instructions for using the Lism CSS framework.\n- [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection as it requires the agent to process external data like design screenshots and user requirements to generate code.\n
- Ingestion points: Design data and requirements processed during the initial implementation phase (SKILL.md, references/authoring.md).\n
- Boundary markers: The instructions do not define specific delimiters for separating user-provided design data from system instructions.\n
- Capability inventory: The skill instructs the agent to generate code and write metadata/verification files (.lism/plan.md, .lism/review.md).\n
- Sanitization: No specific sanitization or filtering of external design inputs is described.\n- [EXTERNAL_DOWNLOADS]: The skill references the installation of official Lism CSS tools (lism-cli, @lism-css/plugin) and documentation. These resources are authored by the skill vendor (lism-css) and are considered safe for the intended use of the framework.
Audit Metadata