moai-foundation-ears

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection through external tool integration.
  • Ingestion points: The skill logic in SKILL.md describes fetching external documentation using the mcp__context7__get-library-docs tool.
  • Boundary markers: There are no explicit delimiters or instructions defined to isolate the external data from the agent's core instructions or to warn against embedded commands.
  • Capability inventory: The skill is granted access to high-privilege tools including Bash, Write, and WebFetch.
  • Sanitization: The skill does not implement any validation or sanitization of the content retrieved from the Context7 documentation library before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:07 AM