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
Critical
Do not install without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/skills-codex/auto-review-loop-minimax/SKILL.mdSecurity
3 findings — 1 critical severity, 2 medium severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
Malicious code pattern detected (high risk: 0.90). This skill instructs automated collection of local project files, experiment outputs, and credentials (reads an API key from ~/.codex/settings.json or env), then sends full research context to an external third‑party MiniMax API and also includes silent file‑write and remote SSH execution directives—behaviors that enable data exfiltration, stealthy modification of files, and remote code execution without explicit user consent.
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: 1.00). This skill submits full project context to the third‑party MiniMax reviewer (via mcp__minimax-chat__minimax_chat or the curl fallback in Phase A and the Prompt Template) and explicitly saves and follows the reviewer's raw response (Phase B → Phase C → Phase E) to implement code changes and run experiments, so untrusted external content can directly drive agent actions.
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 https://api.minimax.io/v1/chat/completions (via curl fallback or possibly via the MCP tool) and explicitly saves and uses the raw reviewer response to decide scores, verdicts, and subsequent code/experiments—so fetched content from that URL directly controls agent behavior.
- Commit
dc00dfb
- 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.