bun-file-io
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill correctly documents standard file system and networking APIs for the Bun runtime. All code snippets use generic placeholder file paths and a documentation-standard placeholder domain (example.com), presenting no inherent risk.
- [INDIRECT_PROMPT_INJECTION]: The skill documents APIs for reading data from external files and URLs into the agent's context, representing a standard attack surface for indirect prompt injection if applied to untrusted sources.
- Ingestion points:
Bun.file().text(),Bun.file().json(), andfetch()calls inSKILL.md. - Boundary markers: None (standard API documentation).
- Capability inventory: File system read/write, directory manipulation, and network requests via
fetch. - Sanitization: The documentation focuses on API mechanics and does not implement input sanitization.
Audit Metadata