beads-create
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with the
bd CLItool to create epics and issues based on user-provided plans. - [DATA_EXPOSURE]: References a hardcoded absolute file path in the author's local development environment (
/Users/btraut/Development/skills-external/beads/SKILL.md). While this points to a specific user's directory, it is used to load additional guidance for the tool. - [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted documents such as PRDs, OpenSpecs, and design docs to generate issues, which could contain instructions meant to influence the agent's behavior.
- Ingestion points: External plans, specs, PRDs, and design documents (SKILL.md).
- Boundary markers: None present; the agent is instructed to translate the plan directly into the Beads structure.
- Capability inventory: The skill uses the
bd CLIto create project hierarchies, epics, and tasks (SKILL.md). - Sanitization: There is no mention of sanitizing or escaping the content of the external plans before processing.
Audit Metadata