beads-workflow

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external markdown plans to generate and polish task descriptions (beads), creating a vulnerability surface.
  • Ingestion points: Instructions in references/plan-to-beads.md and references/polishing-workflow.md direct the agent to read and elaborate on content from external files (e.g., YOUR_PLAN_FILE.md).
  • Boundary markers: There are no explicit instructions or delimiters to isolate the input data or warn the agent to ignore potentially malicious instructions embedded within the processed plan files.
  • Capability inventory: The skill utilizes the bd tool for creating and modifying tasks and the bv tool for graph analysis across multiple files.
  • Sanitization: No evidence of sanitization or validation of the input markdown content is provided before it is used to influence agent actions.
  • [COMMAND_EXECUTION]: The skill relies on the execution of local CLI tools to manage the task lifecycle.
  • Evidence: SKILL.md and references/agent-integration.md specify usage of the bd tool (init, create, update, depend, close) and the bv tool (robot-mode flags for triage and insights) to perform its core functions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 11:51 AM
Security Audit — agent-trust-hub — beads-workflow