axiom-audit-accessibility
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a set of instructions for auditing local source code for accessibility violations. It uses standard pattern-matching techniques and does not engage in network communication, privilege escalation, or access to sensitive user credentials.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted data in the form of local project files which could contain malicious instructions designed to influence the agent's behavior. The risk is considered minimal as the skill lacks capabilities to write to the filesystem or transmit data externally.\n
- Ingestion points: Local project files, specifically .swift files scanned during the audit phases.\n
- Boundary markers: No explicit markers are used to differentiate between code and potential natural language instructions in comments.\n
- Capability inventory: Capabilities are limited to file reading and pattern matching; no network or write access is requested.\n
- Sanitization: No validation or sanitization of the input file content is performed.
Audit Metadata