axiom-audit-textkit
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a set of static analysis procedures using local file system tools (Glob, Grep, and Read). It does not request network access, access sensitive credentials, or perform any persistent system modifications.
- [SAFE]: The instructions focus strictly on technical auditing of iOS and macOS text view implementations. There are no attempts to bypass safety filters or hide malicious intent through obfuscation.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process source code from external projects, which is a potential surface for indirect prompt injection. However, because the skill's activities are limited to read-only analysis and report generation without network or file-write capabilities, this surface is considered low risk and handled by standard platform guardrails.
Audit Metadata