gsd-quick

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to the direct interpolation of user-supplied arguments into the execution context.
  • Ingestion points: User input provided via the {{GSD_ARGS}} placeholder in SKILL.md.
  • Boundary markers: No delimiters or instructions to ignore embedded instructions are utilized during interpolation.
  • Capability inventory: The skill possesses the ability to spawn sub-agents (spawn_agent), modify files (STATE.md), and execute version control commands (atomic commits).
  • Sanitization: User input is processed without any sanitization or validation logic.
  • [COMMAND_EXECUTION]: The skill performs automated file system and version control operations as part of its core workflow.
  • Evidence: The skill objective describes performing 'atomic commits' and maintaining 'state tracking' through STATE.md updates.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 04:33 AM