faion-accessibility-specialist
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- PROMPT_INJECTION (LOW): Potential for Indirect Prompt Injection.
- Ingestion points: The
SKILL.mdfile defines an auto-investigation protocol that ingests untrusted data from.aidocs/constitution.md,.eslintrc,axe.config.js, design tokens, and source code withinsrc/components/. - Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions for content parsed during discovery.
- Capability inventory: The agent has the capability to generate remediation code fixes and produce compliance documentation (VPAT/ACR), which could be influenced by malicious content in ingested data.
- Sanitization: Absent. There is no mention of sanitizing, escaping, or validating external content before it is interpolated into the agent's context.
- NO_CODE (SAFE): No executable scripts or binaries were found within the skill package. The skill consists entirely of Markdown-based educational content and agent instructions.
Audit Metadata