lcx-doctor
Diagnose LazyCodex and Codex CLI installation health against the latest sources. Use whenever the user asks for a doctor or health check, says LazyCodex, lazycodex-ai, omo-codex, or Codex behaves oddly after an install, update, or config change, suspects a stale, drifted, or broken setup, or wants the local install audited and compared with the latest LazyCodex and Codex code.
68
83%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill requires that every verdict "cites the command output or file that produced it" and explicitly instructs reading and citing files like CODEX_HOME/config.toml, which can contain API keys or secrets, so the LLM may be forced to include secret values verbatim in its report.
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 materializes “latest sources” by cloning/fetching public repos (e.g., `gh repo clone` / `git fetch` of `code-yeongyu/lazycodex` and `openai/codex`) into `LAZYCODEX_SOURCE_ROOT`, after which the agent reads installer/runtime files from those checkouts (and thus could ingest outsider-authored free text from those repo files into the LLM context when forming evidence/verdicts).
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 syncs live GitHub repositories during runtime (e.g., via git clone "https://github.com/$REPO" and setting origin "https://github.com/$REPO.git") and calls sync_latest_source on code-yeongyu/lazycodex and openai/codex, so remote repo content directly controls the doctor's comparisons and outputs.
- Repository
- code-yeongyu/lazycodex
- Commit
895b70c
- 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.