moai-core-language-detection

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection vulnerability surface as it is designed to ingest and interpret data from external, untrusted configuration files.\n
  • Ingestion points: The logic in SKILL.md describes reading and parsing data from package.json, pyproject.toml, Cargo.toml, and go.mod.\n
  • Boundary markers: The skill does not define specific delimiters or instructional guardrails to ensure the agent treats the content of these files strictly as data rather than as instructions.\n
  • Capability inventory: The skill uses Read and Bash (grep, ripgrep) tools, which provide the agent with access to the file system and pattern-matching capabilities that could be abused if the agent is manipulated by malicious content within a manifest file.\n
  • Sanitization: There is no evidence of validation or sanitization of the values extracted from file fields (e.g., 'description', 'version', or custom metadata) before they are presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 05:14 PM