llm-council
Orchestrate a configurable, multi-member CLI planning council (Codex, Claude Code, Gemini, OpenCode, or custom) to produce independent implementation plans, anonymize and randomize them, then judge and merge into one final plan. Use when you need a robust, bias-resistant planning workflow, structured JSON outputs, retries, and failure handling across multiple CLI agents.
83
78%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/llm-council/SKILL.mdSecurity
1 medium severity finding. This skill can be installed but you should review these findings before use.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 0.90). The skill explicitly spawns external model CLIs (codex/claude/gemini/opencode or arbitrary custom commands) and ingests their textual outputs into the planning and judging workflow (see scripts/llm_council.py run_planners/run_judge and the SKILL.md Workflow which collect, anonymize, randomize, judge, and merge planner outputs), so untrusted third‑party model responses can materially influence decisions and subsequent actions.
- Repository
- am-will/codex-skills
- Commit
ca2c3b3
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.