Diagnose and fix oh-my-codex installation issues
74%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Medium
Suggest reviewing before use
Fix and improve this skill with Tessl
tessl review fix ./plugins/oh-my-codex/skills/doctor/SKILL.mdThe canonical home for this skill is doctor in Yeachan-Heo/oh-my-codex
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
The skill directs the agent to run `omx setup` and `omx doctor --force`, edit or remove hook registrations and managed files under `~/.codex`, and change AGENTS.md and setup policies, though it avoids sudo, user accounts, and system services and heavily conditions these on authorization.
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.
The required workflow reads the npm registry's published `version` field for oh-my-codex (line 33), which is a public registry lookup, and it reads directory names from the local plugin cache, which may originate from public marketplaces. Local config, hook, AGENTS.md, and skill files are user or organization owned, and the referenced GitHub docs are only cited, not ingested. I classed this as low under the recall-first override because the public registry and marketplace-derived cache names are plausibly outsider-influenced, though the fields read are a version string and paths, not free text.
Yeachan-Heo/oh-my-codex
08d569c
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.