moai-lang-kotlin

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill instructs the agent to retrieve documentation via the mcp__context7__get_library_docs tool, creating a surface for untrusted data ingestion. \n
  • Ingestion points: Documentation is fetched for libraries such as Ktor, Exposed, and Compose Multiplatform (file: SKILL.md).\n
  • Boundary markers: The skill does not provide specific instructions or delimiters to separate fetched documentation from the agent's internal instruction set.\n
  • Capability inventory: The skill itself contains no executable code, shell scripts, or capabilities for file-writing or direct network requests across its definition.\n
  • Sanitization: There are no instructions for the agent to sanitize or validate the content retrieved from external documentation repositories.\n- [Metadata Poisoning] (SAFE): The metadata accurately describes the skill's purpose and does not contain deceptive or malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:24 PM