swift-clean-advisor

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides static guidance for Swift programming and does not perform any dangerous operations such as network requests, file exfiltration, or command execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes external Swift source code, which is a potential ingestion point for indirect instructions. However, the skill lacks the capabilities required to execute malicious payloads, and its impact is limited to text generation. 1. Ingestion points: Analysis of .swift files and user code implementations described in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Text and code generation only; no file-write, network, or subprocess tools detected in any skill files. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 01:40 PM
Security Audit — agent-trust-hub — swift-clean-advisor