accessibility-statement
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's instructions are limited to document generation and data classification based on user-provided audit results. No malicious patterns such as obfuscation, remote code downloads, or credential exposure were found.
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it ingests external audit reports. However, the risk is negligible as its only capability is writing the resulting statement to a local markdown file.
- Ingestion points: Audit reports processed in the workflow (SKILL.md).
- Boundary markers: Not present to separate audit data from generation instructions.
- Capability inventory: Writing content to
ACCESSIBILITY-STATEMENT.md. - Sanitization: No explicit input validation or sanitization routines are described.
Audit Metadata