effect-platform-abstraction
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides comprehensive instructions for spawning child processes and executing shell commands (e.g., git, gzip, ls) using the ChildProcess and ChildProcessSpawner services.
- [PROMPT_INJECTION]: Documentation patterns ingest untrusted data, creating an indirect prompt injection surface. Ingestion points: FileSystem (readFileString), Terminal (readLine), process output (spawner.string), and network responses (HttpClient). Boundary markers: Absent in code examples. Capability inventory: Includes full filesystem access, shell command execution, and network access. Sanitization: No sanitization or validation of the ingested content is demonstrated in the examples.
- [EXTERNAL_DOWNLOADS]: Includes detailed patterns for performing outbound network requests to external domains using the HttpClient service.
Audit Metadata