omh-accessibility-audit
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, such as UI source code, DOM snapshots, and accessibility trees, to generate audits. This creates a potential surface where malicious instructions embedded in the analyzed data could attempt to influence the agent's behavior or audit findings.
- Ingestion points:
SKILL.mddefines several required inputs that come from the user's environment, including target app code, DOM snapshots, and accessibility tree data. - Boundary markers: The instructions do not specify the use of clear delimiters or instructions for the agent to ignore potentially malicious text embedded within the provided UI evidence.
- Capability inventory: The skill produces high-stakes artifacts such as
accessibility_remediation_handoff/v1andaccessibility_audit_verdict/v1, which are used to guide subsequent developer actions. - Sanitization: There is no mention of sanitization or validation routines for the ingested UI data before it is processed by the LLM.
Audit Metadata