moai-lang-sql

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill defines an ingestion surface for indirect prompt injection by processing external data with high-privilege tool access.
  • Ingestion points: The skill accepts language-specific source directories and configuration files as inputs (SKILL.md).
  • Boundary markers: There are no specified delimiters or instructions to the agent to treat external file content as untrusted data.
  • Capability inventory: The skill allows the use of the Bash (terminal) tool, which provides a pathway for ingested instructions to influence command-line operations.
  • Sanitization: No sanitization or validation mechanisms are described to mitigate the risk of malicious instructions within processed files.
  • [NO_CODE]: No functional scripts or executable binaries are included in the skill; all provided files are markdown-based documentation and metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:07 AM