openspec-to-beads

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill generates shell commands for the 'beads' (bd) CLI using data parsed from local markdown files. The templates in templates/issue-creation.md interpolate <task-description> and <gap-description> directly into shell strings without evident sanitization. This could lead to command injection if a task description in openspec/changes/<change>/tasks.md contains shell metacharacters.
  • [PROMPT_INJECTION]: Indirect Prompt Injection: The skill processes untrusted data from project files to drive its execution logic, creating a surface where malicious instructions in a spec could influence agent actions.
  • Ingestion points: Files located in openspec/changes/<change>/, including proposal.md, tasks.md, and spec.md (referenced in SKILL.md Step 1).
  • Boundary markers: None identified; the agent is instructed to read and understand the content directly.
  • Capability inventory: The skill has the ability to execute CLI commands (bd create, bd dep add) which modifies the project's tracking state.
  • Sanitization: No sanitization or validation of the content parsed from markdown files is performed before it is used in command templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:44 PM