The Agent Skills Directory

[SAFE]: The skill performs static analysis of code using standard tools like glob and grep. No malicious patterns, data exfiltration, or unauthorized command execution were detected.
[INDIRECT_PROMPT_INJECTION]: While the skill analyzes external source code which could theoretically contain malicious instructions, this is a known risk for any code-auditing tool. The risk is minimized by the skill's focus on specific API patterns and structural analysis.
Ingestion points: Source code files including .swift, .entitlements, and Info.plist (SKILL.md).
Boundary markers: None explicitly defined for file content in the instructions.
Capability inventory: Tooling includes Glob, Grep, and Read capabilities for file system inspection (SKILL.md).
Sanitization: No content sanitization is performed on the files being audited.

axiom-audit-icloud