typescript-best-practices

Warn

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: MEDIUMPROMPT_INJECTIONCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The 'Uni-pstack Runtime Adapter' section in 'SKILL.md' contains instructions that attempt to override the agent's core operating procedures and model selection.
  • Evidence: 'Apply these overrides before following the original workflow'
  • Evidence: 'Replace upstream Composer, Claude Opus, and other panel defaults with Codex gpt-5.6-sol'
  • Evidence: 'Do not infer Claude model choices from this skill.'
  • [COMMAND_EXECUTION]: The skill explicitly instructs the agent to run CLI commands and workers.
  • Evidence: 'launch Codex CLI workers using the installed pstack skill spawn-codex-worker script or direct codex exec.'
  • Evidence: 'Use the host terminal, browser, review, subagent, and git tools directly.'
  • [REMOTE_CODE_EXECUTION]: The instructions refer to an external, unverified script ('spawn-codex-worker') and a 'pstack skill' that are not included in the provided package.
  • Evidence: Referring to 'installed pstack skill' as a source for executable scripts implies a dependency on external code that has not been audited.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 10, 2026, 04:46 PM