beads-workflow

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the use of several command-line tools, including br (Beads Rust), bv (Beads Visualizer), git, and jq, to manage the task lifecycle, validate dependencies, and synchronize data with remote repositories.
  • [INDIRECT_PROMPT_INJECTION]: The workflow relies on the agent reading and processing external markdown plan files ([YOUR_PLAN_FILE].md) to generate detailed task beads. This presents a potential surface for instructions embedded within a project plan to influence the agent's actions during the conversion process.
  • Ingestion points: SKILL.md and PROMPTS.md instruct the agent to ingest and elaborate on content from external markdown files.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands are included in the prompts provided to the agent.
  • Capability inventory: The agent has the capability to create/modify tasks via br and perform repository operations using git.
  • Sanitization: No explicit sanitization or validation of the input plan's content is described in the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 09:51 AM