omh-running-work-board
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute the shell command
omh coding status-board --jsonto retrieve the current status of coding units. This is a read-only operation intended for the skill's primary purpose of observability. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, creating a potential surface for indirect prompt injection if the ingested content is attacker-controlled.
- Ingestion points: The skill reads 'local coding artifacts' and Hermes system records (
omh_hudrows) to populate the status board (SKILL.md). - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within the ingested data are defined.
- Capability inventory: The skill has the capability to execute shell commands and reference other system skills via
skill_view(SKILL.md). - Sanitization: There is no evidence of sanitization, validation, or escaping of the ingested task metadata before it is processed by the agent.
Audit Metadata