skill-creator

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the subprocess module in scripts/run_eval.py, scripts/improve_description.py, and eval-viewer/generate_review.py to execute system commands. Specifically, it calls the claude CLI tool to run evaluation queries and optimize descriptions, and the lsof utility to manage local network ports for its evaluation viewer.
  • [DYNAMIC_EXECUTION]: In scripts/run_eval.py, the skill dynamically generates and writes markdown command files to the .claude/commands/ directory. These files are used to inject specific skill metadata and descriptions into the execution context of the claude -p CLI tool during evaluation runs.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary workflow involves ingesting and executing user-provided test prompts and input files through subagents. This creates a vulnerability surface for indirect prompt injection.
  • Ingestion points: Untrusted data enters the context via user-defined prompts in evals/evals.json and associated input files.
  • Boundary markers: The instructions do not define strict delimiters or specific 'ignore embedded instructions' warnings for these external prompts.
  • Capability inventory: The skill can execute shell commands via subprocess, write to the filesystem, and spawn new subagent tasks.
  • Sanitization: There is no evidence of sanitization or filtering for the content of user-provided test prompts before they are interpolation into the subagent's task description.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 11:36 AM