gsd-progress

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection.
  • Ingestion points: The skill captures user input following the invocation command in the {{GSD_ARGS}} variable and reads a workflow definition file located at @/mnt/local-analysis/workspace-hub/.codex/get-shit-done/workflows/progress.md.
  • Boundary markers: No delimiters or specific instructions are provided to the agent to distinguish between trusted instructions and potentially untrusted data within the ingested parameters or workflow file.
  • Capability inventory: The skill has the ability to spawn additional agents (spawn_agent) and request user input (request_user_input), which are sensitive operations that could be misdirected via injected instructions.
  • Sanitization: There is no evidence of sanitization, validation, or filtering of the user-provided arguments before they are utilized in the workflow logic.
  • [NO_CODE]: This skill consists entirely of markdown-based instructions and metadata, with no accompanying source code files or executable scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 04:34 AM