desktop-a11y-specialist
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes desktop application source code and UI metadata to perform accessibility audits. This ingestion of external, potentially untrusted data creates a surface where instructions could be embedded within the audited content to influence the agent's behavior. The risk is mitigated by the skill's lack of dangerous capabilities such as network access or shell command execution.\n
- Ingestion points: Application handoffs and audit requests containing external code or UI descriptions (SKILL.md).\n
- Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded content in audited data.\n
- Capability inventory: The skill is restricted to generating structured JSON findings and routing tasks to other specialized agents; no file-writing or network-capable tools are active in the provided context.\n
- Sanitization: No specific sanitization or filtering logic is described for handling the ingested application data.
Audit Metadata