agui-dotnet-human-in-the-loop
Warn
Audited by Snyk on Jun 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). Outsider free text can enter the LLM context when the operating user resumes the paused run by appending the human’s response (e.g.,
AskHuman(...)/answer) asChatRole.Usercontent; that human-provided text is not authored by the operating user and is therefore outsider-authored free text fed back into the model.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (high risk: 1.00). The prompt explicitly shows wrapping and invoking a "delete_file" function and describes pausing/resuming sensitive tool calls that, when approved, will perform destructive filesystem operations—i.e., it enables modification/removal of system files and can change the machine state.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata