axiom-swift-simplifier
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use standard file system tools (Glob, Grep, and Read) to locate and analyze Swift source files. This behavior is consistent with the skill's primary purpose as a code auditor and uses expected platform capabilities.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by scanning all Swift source files (
**/*.swift) within the project workspace. While there are no specific boundary markers mentioned to delimit code content from instructions, the skill lacks dangerous capabilities such as file-write access or network operations, effectively mitigating the risk of instructions embedded in source code comments influencing external systems.
Audit Metadata