axiom-audit-testing
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Swift source code to identify testing anti-patterns, creating an attack surface for indirect prompt injection.
- Ingestion points: The agent is instructed to scan all production and test Swift files (
**/*.swift) usingGlobandReadtools. - Boundary markers: The skill does not implement specific delimiters or instructions to ignore embedded prompts within the source code files.
- Capability inventory: Analysis is performed using
Glob,Grep, andRead. The skill does not specify or require dangerous capabilities such as file-writing or network exfiltration. - Sanitization: Data is analyzed via pattern matching without prior sanitization, which is standard for static analysis tools.
Audit Metadata