figma-slides
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local script
scripts/figma_cmd.mjsusing Node.js to perform slide creation and batch operations in Figma. While this is the intended functionality, it involves executing shell commands with JSON parameters. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to process content from the
online-researchskill. There are no clear boundary markers or instructions to sanitize or ignore malicious directives that might be embedded in external research data, which could cause the agent to generate unintended slide content or structure. - Ingestion points: Data provided by the
online-researchskill or other external context used to populate slides (SKILL.md). - Boundary markers: Absent. The skill does not define delimiters to separate research data from instructions.
- Capability inventory: Execution of
scripts/figma_cmd.mjswhich can create and modify elements on a Figma canvas. - Sanitization: Absent. There is no mention of filtering or validating the external content before it is passed to the Figma bridge.
Audit Metadata