moai-workflow-jit-docs

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to intelligently discover, load, and process documentation from various sources, including untrusted local project files and real-time web research.
  • Ingestion points: Processes content from local files (README.md, docs/), community resources (Stack Overflow, Dev.to), and dynamic WebSearch results as seen in SKILL.md and advanced-patterns.md.
  • Boundary markers: The instructions do not explicitly define strict boundary markers or instructions for the agent to ignore potentially malicious embedded prompts within the documentation it loads.
  • Capability inventory: The skill uses WebSearch and file system reads (fs.readFile) to gather data, which is then provided to the agent to answer user queries.
  • Sanitization: While it implements quality assessment metrics (authority, recency, completeness) in SKILL.md, it lacks explicit sanitization to filter out prompt injection attacks hidden within external documentation content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 12:32 PM
Security Audit — agent-trust-hub — moai-workflow-jit-docs