beads-create
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external, potentially untrusted documents to create tracker issues, creating a surface for indirect instructions.
- Ingestion points: Processes user-provided documents such as "OpenSpec, PRD, design doc" (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the ingested plan data.
- Capability inventory: Executes shell commands for the
bdandbrtrackers, including creating epics, issues, and updating tracker state (SKILL.md). - Sanitization: No specific sanitization, validation, or filtering of the external plan content is mentioned prior to the agent processing the data.
- [COMMAND_EXECUTION]: The skill interacts with the local system by executing shell commands for the
bd(Beads) andbr(beads_rust) CLI tools. This includes commands for creating issues, checking for dependency cycles, and synchronizing state.
Audit Metadata