accessibility-audit

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze Builderius template data via specialized tools, creating an indirect prompt injection surface. This is a core component of its auditing functionality.
  • Ingestion points: Retrieves template state via builderius_builder_get_state as specified in SKILL.md.
  • Boundary markers: The instructions do not provide explicit delimiters for isolating ingested template data.
  • Capability inventory: The skill has the ability to modify the template environment using tools like builderius_builder_update_module_setting and builderius_builder_add_module.
  • Sanitization: No data sanitization steps are defined for the input template modules.
  • [SAFE]: The skill explicitly mandates that the agent must request user approval before applying any fixes or changes, which serves as a critical safety barrier. No malicious obfuscation, privilege escalation, or persistence patterns were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 02:59 PM
Security Audit — agent-trust-hub — accessibility-audit