beads

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the execution of the bd (Beads) CLI tool to perform task management operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external task descriptions via bd show and bd list. This data is processed by the agent, creating a surface for potential instructions embedded in task content.
  • Ingestion points: Data enters the context through bd ready, bd list, and bd show commands (SKILL.md).
  • Boundary markers: No specific delimiters or warnings for the agent to ignore instructions within tasks are provided.
  • Capability inventory: The skill uses bd CLI for task creation, updates, and completion (SKILL.md).
  • Sanitization: There is no evidence of content filtering or sanitization of the task data before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 12:29 AM
Security Audit — agent-trust-hub — beads