gs-openspec-ship

Pass

Audited by Gen Agent Trust Hub on Nov 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts change names from user input and interpolates them into subagent prompts and command lines.
  • Ingestion points: Change names are collected from the /gs-openspec-ship command or prose lists in SKILL.md.
  • Boundary markers: No specific delimiters or instructions to ignore embedded content are defined for these identifiers.
  • Capability inventory: The orchestrator can run Git commands and invoke subagents with file-system access.
  • Sanitization: There is no evidence of input validation for the change name identifiers.
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform standard development tasks using git and openspec CLI tools.
  • [EXTERNAL_DOWNLOADS]: The documentation references downloading tools from the author's GitHub repository (agoodway/goodstack), which is a vendor-controlled source.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 20, 2026, 09:36 AM