probe-rs
Fail
Audited by Snyk on Nov 19, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate probe-rs CLI wrapper with no malicious intent, but its documented
operation_modesafeguard (1/2/3, including "执行前确认" confirm-before-execute) is never implemented in the code, so a user relying on it is misled about the protection they have.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The RTT path (
probe_rs_rtt.pystreaming target log lines viaemit_stream_record) is the only runtime channel carrying text from outside the user's own tooling; it is firmware output from the target device, which an outsider could influence only if the firmware echoes external input, so I'm rating it low under the recall-first override.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.30). The skill is a probe-rs debugging wrapper whose operations target the embedded board, not the host; the only host-level change it mentions is the conditional advice to switch J-Link to WinUSB, which alters driver bindings but is not an instruction to the agent to perform it.
Issues (3)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata