Fluxwing Component Viewer
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and displays content from external files which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Reads component metadata (
.uxm) and ASCII templates (.md) from./fluxwing/components/,./fluxwing/library/, and sibling template directories. - Boundary markers: The instructions do not specify the use of delimiters or warnings to the agent to ignore instructions embedded within the component files.
- Capability inventory: The skill is limited to
Read,Glob, andGreptools, which restricts the potential impact of an injection to local information gathering. - Sanitization: No validation or sanitization logic is provided to filter out potentially malicious prompt content from the read files before they are processed by the agent.
Audit Metadata