moai-workflow-jit-docs
Warn
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
- Prompt Injection (MEDIUM): The skill is vulnerable to Indirect Prompt Injection due to its core function of loading external content into the agent context.
- Ingestion points: External data is ingested via the
WebFetchandWebSearchtools, as well as local files throughRead,Grep, andGlobtools. - Boundary markers: The implementation guide does not specify the use of delimiters or 'ignore' instructions when processing retrieved documentation.
- Capability inventory: The skill possesses network access (
WebFetch,WebSearch) and local file read access (Read,Grep,Glob), creating a path for data exfiltration if the agent is misled by injected instructions. - Sanitization: The instructions do not define any sanitization, filtering, or validation steps for the content retrieved from external sources before it is utilized by the agent loop.
Audit Metadata