skills/dev-formata-io/limitr/stof/Gen Agent Trust Hub

stof

Pass

Audited by Gen Agent Trust Hub on Nov 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill teaches the AI agent to interpret and execute Stof documents which can contain embedded logic, creating an ingestion surface for potentially untrusted code.\n
  • Ingestion points: The skill documents the use of import and Std::parse to load and execute logic from external files or strings (SKILL.md, Std.md).\n
  • Boundary markers: The documentation explicitly advocates for the use of the untrusted profile and the seal function for confinement when handling external sources (SKILL.md, Std.md).\n
  • Capability inventory: The language supports HTTP fetch (Http.md), file system read/write (fs.md), environment variable access (Std.md), and dynamic code parsing (Std.md).\n
  • Sanitization: The guide provides clear instructions on restricting library access and using object-level sandboxing (confinement) to protect the host document (SKILL.md).\n- [EXTERNAL_DOWNLOADS]: The Http library provides the agent with functions to perform asynchronous network requests to external domains.\n
  • Evidence: Documentation of Http::fetch in references/libs/Http.md.\n- [COMMAND_EXECUTION]: The skill documents capabilities for the agent to interact with the local file system and manage environment variables.\n
  • Evidence: fs::read, fs::write, and fs::read_string documented in references/libs/fs.md; Std::env and Std::set_env documented in references/libs/Std.md.\n- [DYNAMIC_EXECUTION]: The skill includes functions that allow for the parsing and execution of Stof code strings at runtime, which is a core feature of the runtime.\n
  • Evidence: Std::parse and Runtime::call_source are documented as primary methods for dynamic logic processing (SKILL.md, Std.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 21, 2026, 02:37 AM