simulator-automation

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface due to the ingestion of external application data.
  • Ingestion points: The skill reads console logs, exceptions, and failed network requests from the simulator webview via the /api/console endpoint in SKILL.md.
  • Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat content from the logs as untrusted or to ignore instructions embedded within them.
  • Capability inventory: The agent is granted capabilities such as Bash, Write, and Edit, which could be exploited if the agent follows malicious instructions found in the logs.
  • Sanitization: No filtering or sanitization of the log content is described or implemented to prevent the processing of potential injection payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 09:56 PM
Security Audit — agent-trust-hub — simulator-automation