ss-reference
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: Workflow Step 1 explicitly directs the agent to ingest supplied references, including URLs, screenshots, and Figma exports.
- Boundary markers: The instructions do not provide delimiters or specific directives telling the agent to treat external content as data only or to ignore instructions embedded within that content.
- Capability inventory: The skill has access to powerful tools such as
Bash,WebFetch,Write, andEdit(listed inallowed-tools), which could be exploited if an external source contains malicious instructions that the agent follows. - Sanitization: There are no instructions for sanitizing, validating, or filtering content retrieved from external URLs or files before it is processed by the agent.
Audit Metadata