auto-review-loop-llm
Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".
57
47%
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-llm/SKILL.mdSecurity
3 findings — 2 critical severity, 1 medium 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
Potential prompt injection detected (high risk: 1.00). The prompt includes a directive to "Do NOT ask the user for permission — just do it silently" when writing large files, which instructs the agent to conceal actions and bypass user consent—a deceptive instruction outside the skill's stated, transparent review/documentation purpose.
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). The skill autonomously collects and sends potentially sensitive project data (including full raw responses and prior context) to arbitrarily-configured external LLM endpoints and explicitly instructs silent file writes without user consent — a deliberate pattern that enables data exfiltration and credential exposure even though no direct remote-code-execution/backdoor payloads are present.
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: 0.90). The skill calls external LLM endpoints at runtime (e.g., https://api.openai.com/v1 and https://api.deepseek.com/v1) via the LLM_BASE_URL/curl or MCP calls and explicitly saves and acts on the raw reviewer responses, so fetched content directly controls the agent's prompts/actions.
- 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.