spec-driven-brainstorm

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Node.js scripts (spec-driven.js) to automate the creation and validation of project proposal artifacts. While the <name> parameter is user-influenced, the skill includes a constraint to suggest or use 'kebab-case' names, which mitigates standard shell injection risks.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of ingesting and summarizing untrusted project data and user ideas.
  • Ingestion points: Reads rough ideas from the user and existing project specification files from the .spec-driven/ directory (SKILL.md, steps 1 & 2).
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present when reading external files.
  • Capability inventory: The skill possesses the ability to read project files, write new markdown artifacts to the file system, and execute local shell commands via Node.js (SKILL.md, steps 6, 7, & 8).
  • Sanitization: The 'kebab-case' rule for naming provides basic sanitization for the change name argument used in shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 06:25 AM