skills/rmyndharis/antigravity-skills/accessibility-compliance-accessibility-audit/Gen Agent Trust Hub
accessibility-compliance-accessibility-audit
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- Prompt Injection (SAFE): No attempts to override agent behavior, bypass safety filters, or extract system prompts were detected. The instructions are focused solely on WCAG compliance auditing.
- Data Exposure & Exfiltration (SAFE): No hardcoded credentials, sensitive file paths, or network communication commands (e.g., curl, wget) are present in the provided file.
- Remote Code Execution (SAFE): No external dependencies, package installations, or remote script execution patterns were found. The skill is entirely instructional markdown.
- Indirect Prompt Injection (LOW): The skill is intended to process external data (web pages and design artifacts). While this constitutes an ingestion surface for untrusted data, the skill lacks any dangerous capabilities (such as file writing, shell execution, or network egress) that would allow such an injection to be exploited. There are no boundary markers or sanitization steps mentioned for this data, which is common for instructional skills.
Audit Metadata