High-risk tools in Orpheus
7 of the 39 tools in Orpheus are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
apply_changesExecuteapply_changes
-
apply_master_matchExecuteThe spectral half: render the master → Matchering against the fingerprint's
-
build_project_specExecuteFuse symbolic + audio analysis into one CompositionSpec(current) + a plain-English
-
explain_styleExecute"Why does this sound like X?" — run feature thresholds over the current project and
-
play_stop_recordExecuteTransport control: 'play' | 'stop' | 'record', via Main_OnCommand action IDs.
-
render_and_auditExecuteRender, then measure LUFS/spectrum in one call so the agent self-checks
-
render_projectExecuteHeadless render to WAV/MP3 (RENDER_FILE + format/bounds + Main_OnCommand(41824)).
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.