skills/agfnow/agentflow/aglite/Gen Agent Trust Hub

aglite

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands for Git operations, browser automation (via the Browserbase browse CLI), and external agent reviews. It incorporates defensive programming guidelines, specifically instructing the agent to use literal argument arrays and heredocs to prevent command injection.
  • [REMOTE_CODE_EXECUTION]: The skill facilitates multi-agent delegation through spawn_agent and external CLI interfaces (codex, claude). It mitigates risks by enforcing context isolation (e.g., fork_turns: "none") and requiring that sub-agents treat instructions found in repository files as data rather than executable authority.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local repository files such as AGENTS.md and rules.md. It includes explicit instructions to treat this external content as untrusted data that cannot override the skill's core logic or the agent's safety guidelines.
  • [CREDENTIALS_UNSAFE]: The instructions include mandatory requirements to redact credentials and sensitive information from all captured logs, notebook entries, and reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 11:52 AM