eli

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied topics through the $ARGUMENTS variable to generate HTML artifacts. This creates a surface where malicious input could attempt to influence the generated code. Ingestion points: $ARGUMENTS in SKILL.md. Boundary markers: Absent. Capability inventory: Generates HTML, CSS, and JavaScript via the Artifact tool. Sanitization: Absent.
  • [DYNAMIC_EXECUTION]: The skill generates vanilla JavaScript code for interactive simulators within the artifacts. This is restricted to self-contained logic and occurs within a sandboxed environment.
  • [SAFE]: No security issues such as data exfiltration, credential theft, or unauthorized command execution were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 03:05 AM
Security Audit — agent-trust-hub — eli