skills/kursku/skills/gsd-quick/Gen Agent Trust Hub

gsd-quick

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill captures user input via the {{GSD_ARGS}} placeholder to define task parameters for sub-agents. \n
  • Ingestion points: User input following the $gsd-quick trigger is captured in the {{GSD_ARGS}} variable within SKILL.md. \n
  • Boundary markers: The skill instructions do not define specific delimiters or guardrail instructions to isolate the user-interpolated input from the agent's internal logic. \n
  • Capability inventory: The skill utilizes the spawn_agent tool to create sub-tasks and is designed to perform filesystem writes, including atomic commits and state tracking in STATE.md. \n
  • Sanitization: No sanitization, filtering, or validation of the input arguments is described in the skill's processing logic. \n- [COMMAND_EXECUTION]: The skill references a local file at a hardcoded absolute path (C:/Users/nicol/.codex/get-shit-done/workflows/quick.md) for its execution context and process definition. This creates a dependency on a specific local environment and file structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 12:01 PM
Security Audit — agent-trust-hub — gsd-quick