hc
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions in SKILL.md utilize a suite of hive hc CLI commands to manage task and epic lifecycles within an agent's workflow.
- [INDIRECT_PROMPT_INJECTION]: The skill implements a workflow where arbitrary text strings (titles, descriptions, comments) are ingested and later presented to agents via the hive hc context command, creating an injection surface.
- Ingestion points: Task metadata and comments are ingested via hive hc create, hive hc update, and hive hc comment in SKILL.md.
- Boundary markers: The skill does not define specific delimiters or safety instructions in SKILL.md for the agent to use when processing the aggregated context block.
- Capability inventory: The skill provides task coordination and state management capabilities through the hive command-line tool.
- Sanitization: SKILL.md does not describe any sanitization or filtering of the user-provided text before it is presented to subsequent agents in the prompt context.
Audit Metadata