moai-lang-cpp

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by design as it is intended to read and analyze external source code and configuration files.
  • Ingestion points: Ingests data from language-specific source directories, configuration files, and test suites as specified in SKILL.md.
  • Boundary markers: Absent. The skill provides no specific delimiters or instructions to the agent to disregard potential commands embedded within the analyzed files.
  • Capability inventory: The agent is granted powerful capabilities including terminal access (Bash), file system access (Read), and network access (WebFetch and WebSearch).
  • Sanitization: No sanitization, validation, or filtering procedures for external file content are defined.
  • [NO_CODE]: The skill consists entirely of instructional markdown files and does not distribute any executable scripts or binary files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 05:15 PM