auto-review-loop-minimax
Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".
81
76%
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/skills-codex/auto-review-loop-minimax/SKILL.mdSecurity
2 findings — 2 medium severity. 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 sends full project context to the external MiniMax reviewer (via mcp__minimax-chat__minimax_chat or curl to https://api.minimax.io/) and explicitly saves and parses the reviewer's "FULL raw response" (appended to review-stage/AUTO_REVIEW.md) to extract score/verdict/action items that directly drive code changes, experiments, and loop decisions, so untrusted third‑party content can change agent behavior.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 1.00). The skill issues runtime calls to the MiniMax API (curl to "https://api.minimax.io/v1/chat/completions"), saves the raw model response verbatim, and uses that remote content to determine scores, verdicts and concrete action items that drive code changes and experiment execution, so the fetched content directly controls agent behavior.
- Commit
700fbe2
- 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.