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".
48
51%
Does it follow best practices?
Impact
—
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-llm/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: 0.85). The skill’s Phase E explicitly appends the **reviewer’s raw response** (which is generated from the external LLM/MCP server) into `review-stage/AUTO_REVIEW.md` and also uses that response for parsing in Phase B; this is **outsider-authored free text** coming from the external reviewer/LLM runtime path (`mcp__llm-chat__chat` → raw response → saved/pasted into LLM context on later rounds via “Previous Review Summary”/included context).
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 performs runtime calls to the LLM endpoint pattern "${LLM_BASE_URL}/chat/completions" (e.g., https://api.deepseek.com/v1 or https://api.openai.com/v1) via curl/MCP to fetch reviewer responses which are saved verbatim and whose score/verdict/action items directly control the agent's next actions and loop behavior, so this external content directly controls prompts/execution.
- Commit
de05de7
- 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.