amc-run-rtsp-calibration
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill includes explicit instructions and logic to protect sensitive data. It warns against printing RTSP credentials or bearer tokens in logs or chat interfaces. The bundled Python script implements a redaction function (
_redact_rtsp_url) that sanitizes URLs before they are displayed in the plan summary, preventing accidental exposure of embedded credentials. - [PRIVILEGE_ESCALATION]: The instructions involve the use of
dockercommands to interact with the AutoMagicCalib microservice container. These operations are scoped to the specific service stack and are intended for retrieving runtime configuration (likeVIOS_BASE_URL) or applying temporary environment overrides during troubleshooting, which is consistent with the skill's administrative purpose. - [DYNAMIC_EXECUTION]: The skill utilizes a bundled Python script for its primary logic. The shell instructions for running this script include a path discovery loop that searches within known project and agent-specific skill directories. The script itself performs its tasks using standard library calls and the
requestspackage for API communication without using unsafe dynamic evaluation of external input.
Audit Metadata