accessibility-annotations
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill contains logic patterns for runtime JavaScript execution within a Figma environment. As detailed in
figma-tooling.md, it defines a 'recipe' for cloning nodes, dynamically updating properties usingsetProperties, and implementing font fallback handlers viafigma.loadFontAsync. The agent is expected to generate and execute these scripts using an environment-provided tool likefigma-useto interact with the Figma API.\n- [INDIRECT_PROMPT_INJECTION]: The skill operates by reading and processing content from external, untrusted sources which could contain malicious instructions designed to influence agent behavior during the annotation process.\n - Ingestion points: The project handoff document (referenced in
handoff-template.md) and metadata/text from Figma canvas nodes (referenced inSKILL.md).\n - Boundary markers: Absent; there are no instructions to utilize delimiters or system prompts to ignore embedded instructions within the ingested handoff data.\n
- Capability inventory: The skill possesses significant 'write' capabilities in the Figma document, including creating new nodes, modifying text properties, and altering layer hierarchies as specified in
SKILL.mdandfigma-tooling.mdvia the Figma write tool.\n - Sanitization: Absent; the logic in
figma-tooling.mdandSKILL.mddescribes direct interpolation of data into component properties without mention of validation or output encoding.
Audit Metadata