pencil-ui-design-spec-generator
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides links to documentation and usage guidelines for Pencil MCP tools. These resources are hosted in the
full-stack-skillsGitHub organization, which corresponds to the skill's author. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an ingestion surface for untrusted data as it processes user requests to generate design plans.
- Ingestion points: User request processing described in SKILL.md.
- Boundary markers: The skill enforces a strict output format (PENCIL_PLAN), though it lacks specific instructions to ignore embedded commands in the input.
- Capability inventory: No execution capabilities detected; the skill only generates text-based plans. It does not write files, execute subprocesses, or perform network operations.
- Sanitization: No explicit sanitization or filtering of input data is defined.
- [NO_CODE]: The skill contains only documentation and instructional files. No executable scripts or binaries are included.
Audit Metadata