skills/varlabz/skills/skill-creator/Gen Agent Trust Hub

skill-creator

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands using Python's subprocess module to invoke the pi CLI tool for testing and optimization tasks (scripts/run_eval.py, scripts/improve_description.py). It also utilizes lsof to manage local network ports for its evaluation viewer (eval-viewer/generate_review.py).
  • [EXTERNAL_DOWNLOADS]: The evaluation report viewer (eval-viewer/viewer.html) loads the SheetJS library from cdn.sheetjs.com. This is a well-known service for client-side spreadsheet processing.
  • [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface by ingesting and processing external data from subagent transcripts and user-provided feedback files. These ingestion points (e.g., feedback.json, transcript.md) are used to drive the agent's grading and improvement logic. While the skill possesses capabilities like shell command execution, the instructions provide a structured workflow for handling this data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 02:16 AM
Security Audit — agent-trust-hub — skill-creator