skills/thinkgem/skills/quick-start/Gen Agent Trust Hub

quick-start

Warn

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a local shell command: python3 scripts/cache_docs.py --skill quick-start --permalink <permalink>. This script is responsible for downloading and updating documentation from the JeeSite platform.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection (Category 8) because it uses user queries to determine the parameters for the documentation retrieval script.
  • Ingestion points: User questions regarding the JeeSite platform (e.g., "What is JeeSite?", "Architecture features").
  • Boundary markers: None identified. The skill relies on the agent correctly matching a question to a permalink in a static table.
  • Capability inventory: Execution of shell commands via the python3 interpreter (SKILL.md).
  • Sanitization: There is no explicit evidence of sanitization for the permalink argument before it is passed to the command line, creating a surface for command injection if the agent or the underlying script does not validate the input.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 9, 2026, 03:14 AM
Security Audit — agent-trust-hub — quick-start