swiftdata-pro
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed exclusively of documentation files and metadata. It does not include any Python or Node.js scripts, binary executables, or other active components that could perform malicious actions. \n- [EXTERNAL_DOWNLOADS]: The skill references other repositories on GitHub (swift-concurrency-agent-skill and swiftui-agent-skill) authored by the same developer (twostraws). These references are used solely for providing further educational context and do not trigger any automated downloads or code execution. \n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and review untrusted user-provided Swift code. \n
- Ingestion points: User-provided code snippets in the chat interface as instructed in SKILL.md. \n
- Boundary markers: None present in the skill instructions to delimit user input from system prompts. \n
- Capability inventory: No executable capabilities (such as subprocess calls, eval/exec, file-write, or network operations) are present in the skill files. \n
- Sanitization: No sanitization or escaping of external content is performed. Due to the total absence of exploitable capabilities, this surface presents no practical security risk.
Audit Metadata