ui-color-palette-generate-semantic-code
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests complex user-provided objects (
base,themes,system) to generate code, which represents an indirect prompt injection surface. - Ingestion points: Input parameters for the
generate_codetool inSKILL.md. - Boundary markers: Absent; the skill does not instruct the agent to use specific delimiters or ignore instructions within the input data.
- Capability inventory: Invokes the
ui-color-palette:generate_codetool and suggests usinggh-cliorgitlab-cli-skillsfor file persistence. - Sanitization: None described; the skill assumes valid configuration objects from the user or context.
Audit Metadata