axiom-ios-performance
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): The content consists of legitimate routing logic and instructional guidance for iOS performance debugging. There are no attempts to override agent behavior, bypass safety filters, or extract system prompts.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network operations were found. The skill does not access or transmit user data externally.
- [Remote Code Execution] (SAFE): While the skill mentions command-line tools such as
xctrace, it acts as a reference and routing mechanism rather than executing arbitrary or untrusted remote scripts. - [Obfuscation] (SAFE): The content is entirely human-readable with no use of Base64 encoding, zero-width characters, or homoglyphs.
- [Persistence & Privilege Escalation] (SAFE): No commands related to administrative privileges (
sudo) or system persistence (cron, startup scripts) were identified.
Audit Metadata