consistency-audit-beads

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes multiple commands using the bd (Beads) CLI tool to manage project issues, including bd init, bd create, bd update, and bd dep add. There is a risk of command injection if project metadata or user-supplied arguments interpolated into these shell commands contain unescaped characters or subshells.
  • [EXTERNAL_DOWNLOADS]: The skill references the beads-cli Python package and provides installation instructions via pip if the tool is missing. It also links to the developer's GitHub repository for the tool.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted project content to perform its audit. * Ingestion points: Local project source files and user interface prototypes audited during Phase 1. * Boundary markers: None present; the instructions do not include delimiters or warnings to ignore instructions embedded in the audited content. * Capability inventory: The skill can write documentation files (docs/hci/consistency-audit.md) and execute shell commands via the bd CLI tool. * Sanitization: No sanitization or validation of the audited content is performed before it is used to generate findings or CLI command arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 04:53 PM
Security Audit — agent-trust-hub — consistency-audit-beads