oc-orchestrator
Warn
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: MEDIUMPERSISTENCEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PERSISTENCE]: The skill describes a 'Self-improvement' workflow where the
oc-toolsmithsubagent authors new tools and saves them to a git-trackedtoolbox/directory. These tools are explicitly designed to persist across runs and are described as being 'reusable by every future run.' - [DYNAMIC_EXECUTION]: The skill facilitates the runtime generation and execution of code. When standard tools are insufficient, the
oc-toolsmithagent writes new tool scripts which are subsequently executed via theoc toolbox runcommand. - [INDIRECT_PROMPT_INJECTION]: The skill implements a 'steering' system that allows external directives to influence subagent behavior.
- Ingestion points: The orchestrator reads directives from the
open_steeringfile (accessed viaoc status) and project manifests. - Boundary markers: No markers or delimiters are specified; instructions mandate folding directives 'into the prompt' verbatim and require workers to 'honor steering over its own default judgment.'
- Capability inventory: The skill has the capability to spawn subagents via the
Agenttool and execute shell commands via theBashtool. - Sanitization: The skill does not mention any sanitization or validation of the input retrieved from the
open_steeringsource. - [COMMAND_EXECUTION]: The skill relies on the
Bashtool to interact with theocCLI suite for video ingestion, processing, and management of the dynamic toolbox.
Audit Metadata