accessibility-testing
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from external sources, specifically the accessibility tree (labels, hints, and values) of iOS applications under test.
- Ingestion points: The skill utilizes the output of
idb-ui-describe, which contains accessibility metadata defined by application developers. - Boundary markers: The instructions do not define specific delimiters or guardrails to separate application metadata from the agent's internal logic during analysis.
- Capability inventory: The skill uses tools for UI inspection (
idb-ui-describe,idb-ui-find-element,accessibility-quality-check) and visual verification (screenshot). - Sanitization: There is no evidence of sanitization or filtering applied to the accessibility labels before they are processed by the agent. While this represents a theoretical vulnerability surface for indirect prompt injection, it is inherent to the nature of UI testing and does not indicate malicious intent in the skill itself.
Audit Metadata