skills/managedcode/dotnet-skills/fsi/Gen Agent Trust Hub

fsi

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses dotnet fsi to run a REPL environment and execute .fsx scripts via the shell.
  • [EXTERNAL_DOWNLOADS]: The skill supports downloading and referencing external libraries using the #r "nuget: ..." directive, which fetches packages from the NuGet registry.
  • [DYNAMIC_EXECUTION]: By design, the skill provides an interactive environment (REPL) and script interpreter for dynamic F# code execution.
  • [PRIVILEGE_ESCALATION]: The documentation includes instructions to use chmod +x to grant execution permissions to local F# scripts on Unix-like systems.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for reading and summarizing external text files (e.g., input.log), which represents a potential attack surface for indirect prompt injection if those files contain malicious instructions.
  • Ingestion points: File.ReadLines path in the 'Read And Summarize Text' pattern.
  • Boundary markers: None identified in the provided patterns.
  • Capability inventory: File system writes (File.WriteAllLines), console output, and dynamic code execution.
  • Sanitization: No specific sanitization or filtering of external content is implemented in the provided examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 07:34 AM
Security Audit — agent-trust-hub — fsi