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".
66
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Security
2 findings: 2 critical severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E004: Prompt injection detected in skill instructions.
What this means
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
Why it was flagged
The skill includes an explicit, deceptive instruction to perform file writes "silently" without asking the user for permission (SKILL.md:222), which instructs hidden behavior outside normal autonomous review operations.
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
The skill contains explicit instructions to send full project context (including potential secrets) to an external provider, to act on/shell out to remote servers based on untrusted reviewer responses, and to perform silent file writes without asking the user — enabling data exfiltration and remote-execution/backdoor abuse.
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
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
The required workflow sends the external reviewer’s verbatim free-text response (outsider-authored) back into the agent’s subsequent LLM context via the “For round 2+, include the summary of previous review feedback and changes in the prompt itself” / “Save the FULL raw response … store in a variable for Phase E” loop, creating an indirect prompt-injection path.
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
The skill makes runtime curl calls to https://api.minimax.io/v1/chat/completions to fetch reviewer text that is saved verbatim and used to determine and implement fixes, so external content directly controls the agent's actions.
- Commit
f4f20f9
- 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.