accessibility-expert
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): The skill is entirely declarative and instructional. There is no code (Python, JavaScript, or Shell) associated with the skill, which eliminates vectors for remote code execution, command injection, or privilege escalation.
- PROMPT_INJECTION (SAFE): The instructions do not contain markers intended to bypass AI safety filters or override system prompts. The language is focused on accessibility domain expertise.
- DATA_EXFILTRATION (SAFE): No hardcoded credentials, sensitive file path references, or network-bound operations (e.g., curl, fetch) are present.
- INDIRECT_PROMPT_INJECTION (LOW): While the skill is designed to ingest and audit user-provided code and components, it lacks any tool-calling capabilities or file-writing permissions that could be exploited if malicious instructions were embedded in the processed data. (Ingestion: User-provided components via SKILL.md instructions; Boundary markers: Absent; Capability inventory: None; Sanitization: None).
Audit Metadata