omh-deliverable-package
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the
omhcommand-line utility to record the runtime status of the workflow (e.g.,omh runtime record --skill deliverable-package --harness deliverable-package --status started). This is a standard operation within the intended framework environment. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data, specifically user requests and target contexts, which introduces a potential surface for indirect prompt injection.
- Ingestion points: The skill ingests data from fields such as
user requestandtarget contextas specified in the Required Inputs section ofSKILL.md. - Boundary markers: The instructions explicitly require the agent to maintain a "prepared-vs-observed boundary" and to use "wrapper actions" to delimit workflow orchestration from actual evidence.
- Capability inventory: The skill utilizes a specific subprocess call to the
omhCLI tool for status recording withinSKILL.md. - Sanitization: The skill instructs the agent to "expose missing tools, credentials, targets, or observations as user-visible gaps" rather than blindly obeying instructions within the processed data.
Audit Metadata