The Agent Skills Directory

[SAFE]: No security issues were detected. The skill acts as a read-only auditor for Swift code, prioritizing readability and idiomatic improvements. All operations are local and involve standard search and read tools.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by reading local Swift files using tools like Glob, Grep, and Read. While this represents an attack surface for indirect prompt injection, the agent's capabilities are restricted to auditing and reporting findings. It has no capabilities for file modification, network operations, or shell execution that could be exploited via malicious content in the scanned files. Findings for this category are considered safe due to the limited capability tier.

axiom-swift-simplifier