axiom-ios-data
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [No Code] (SAFE): The skill consists entirely of markdown instructions and routing logic. There are no scripts (.py, .js, .sh), binaries, or configuration files that execute logic on the host system.
- [Safe Routing] (SAFE): The instructions provide a decision tree for the agent to select other skills (e.g.,
axiom-swiftdata,axiom-cloud-sync). This is a standard architectural pattern for organizing complex AI tasks and does not introduce security vulnerabilities. - [No Data Risk] (SAFE): Analysis of the content reveals no hardcoded credentials, sensitive file path references, or network exfiltration patterns. The skill operates within the context of providing development guidance.
- [Prompt Integrity] (SAFE): While the instructions use authoritative language ("You MUST", "ALWAYS"), these are directed at ensuring the agent uses the correct specialized sub-skills for data safety (e.g., migrations) and do not attempt to bypass AI safety guardrails or extract system prompts.
Audit Metadata