beads
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the
bd(Beads) CLI tool to perform project management tasks. It instructs the agent to execute various shell commands includingbd prime,bd ready,bd list,bd show,bd update,bd create, andbd close. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes task descriptions which may contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Task content is ingested from the repository's Beads workspace via
bd listandbd show <id>inSKILL.md. - Boundary markers: The skill does not define clear boundaries or provide instructions to the agent to treat task content as untrusted data.
- Capability inventory: The agent can modify project state through the
bd update,bd create, andbd closecommands. - Sanitization: There is no evidence of sanitization or filtering of task content before it is processed by the agent.
Audit Metadata