First Seen
Feb 18, 2026
Last Scanned
Feb 20, 2026
Findings
2
Score
85/100
Findings (2)
Detects instructions to decode and execute base64 content
Base64`](references/useBase64Remove text that simulates multi-turn conversations or fake user/assistant message pairs. These patterns attempt to manipulate the agent by fabricating conversation history.
Likely FP if the matched text is documentation showing example conversations or API request/response formats for illustration purposes.
Detects URLs fetched at runtime that control or influence agent behavior without pinning
read and write local files with [FileSystemAccessAPI](https:// + ruleAvoid loading configuration or behavior-controlling content from runtime URLs. Bundle required configurations locally or pin remote config to versioned, integrity-verified endpoints.
Likely FP if the URL in the match is a documentation link or example URL (e.g., example.com) rather than an actual runtime-fetched configuration endpoint.