extract-color
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill generates small JavaScript snippets (limited to 50 lines) to be executed at runtime via the
figma_executeoruse_figmatools. This occurs during the optional Step 3-delta phase to resolve missing data points from the Figma environment. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data which could influence its behavior.
- Ingestion points: Untrusted data enters the agent context through
_base.json,optionalContext, andapi-dictionary.json(SKILL.md, Steps 2 and 2.5). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to wrap external content during interpolation.
- Capability inventory: The skill possesses the ability to write JSON files to the local cache and execute commands via MCP tools (SKILL.md, Step 3-delta and Step 7).
- Sanitization: No explicit sanitization, validation, or escaping of the ingested external content is defined in the workflow.
Audit Metadata