axiom-audit-accessibility
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as a static analysis auditor, utilizing read-only file system tools (Glob, Grep, Read) to scan for accessibility anti-patterns in Swift source code. It does not request network access, perform data exfiltration, or attempt to execute any external scripts.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted source code provided by the user. While it lacks explicit sanitization for this content, its capabilities are restricted to read-only operations and reporting findings, which significantly limits the risk of exploitation. The ingestion points are the file-reading tools used to scan the project hierarchy.
- [COMMAND_EXECUTION]: The skill uses local CLI tools (Glob, Grep) for pattern matching. These are used as intended for static analysis of local files and do not incorporate unvalidated user input into shell commands in a way that would allow for command injection.
Audit Metadata