Agent skill · Audited from source
openai-docs-skill
skill · am-will/codex-skillsLicence not declaredAudited 27 Oct 2026 · source 31eb89d791f0
Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit 31eb89d791f0 and observed network access and no hard-coded secrets. The audit raised 2 findings, 0 critical or high. What it does: Query the OpenAI developer documentation via the OpenAI Docs MCP server using CLI (curl/jq). Use whenever a task involves the OpenAI API (Responses, Chat Completions, Realtime, etc.), OpenAI SDKs, ChatGPT Apps SDK,…
Cite
Cite this page
ModelsAtlas. “openai-docs-skill (am-will/codex-skills)”. Retrieved 27 Oct 2026. https://modelsatlas.com/skills/am-will/openai-docs-skill
Trust audit
Audit 0.4.1 · source read 27 Oct 2026
CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 13,985 of 14,816 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkDeclared1 observation
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 1 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | PASS | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | WARN | 1 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass, no license.
Findings (2)
MEDIUMPrivilege escalation / persistencereview.unsafe_action · SKILL.md
Query the MCP server via the CLI wrapper in `scripts/openai-docs-mcp.sh` (do not rely on Codex MCP tools).
- Why
- Instructs the agent to bypass the native MCP tooling in favor of a bundled script whose contents it must trust.
- Fix
- rewrite it so the instruction says plainly what it does, and asks the user before it acts
LOWInventory / provenanceinv.no_license
- Why
- no LICENSE file and no repo licence
- Fix
- add a licence
Audit 0.4.1 · source sha 31eb89d791f0 · 27 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publisheram-will GitHub userOwner of the repository this skill is read from
- Source folderam-will/codex-skills/skills/openai-docs-skillThe exact folder we audited
- LicenceNot declaredAs the repository states it
- Commit pinned for this verdict31eb89d791f0A new audit runs when the source changes
- Repository statusNot archivedLast push 104 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Query the OpenAI developer documentation via the OpenAI Docs MCP server using CLI (curl/jq). Use whenever a task involves the OpenAI API (Responses, Chat Completions, Realtime, etc.), OpenAI SDKs, ChatGPT Apps SDK,…
--- name: openai-docs-skill description: Query the OpenAI developer documentation via the OpenAI Docs MCP server using CLI (curl/jq). Use whenever a task involves the OpenAI API (Responses, Chat Completions, Realtime, etc.), OpenAI SDKs, ChatGPT Apps SDK, Codex, MCP integrations, endpoint schemas, parameters, limits, or migrations and you need up-to-date official guidance. --- # OpenAI Docs MCP Skill ## Overview Use the OpenAI developer documentation MCP server from the shell to search and fetch authoritative docs. Always do this for OpenAI platform work instead of relying on memory or non-official sources. ## Core rules - Always use this skill for OpenAI API/SDK/Apps/Codex questions or when precise, current docs are required. - Query the MCP server via the CLI wrapper in `scripts/openai-docs-mcp.sh` (do not rely on Codex MCP tools). - Use `search` or `list` to find the best doc page, then `fetch` the page (or anchor) for exact text. - Surface the doc URL you used in your response so sources are clear. ## Quick start ```bash scripts/openai-docs-mcp.sh search "Responses API" 5 scripts/openai-docs-mcp.sh fetch https://platform.openai.com/docs/guides/migrate-to-responses ``` ## Workflow 1. Discover: `search` with a focused query. If unsure, use `list` to browse. 2. Read: `fetch` the most relevant URL (optionally add an anchor). 3. Apply: summarize and/or quote relevant sections; include the URL. ## Script reference The CLI wrapper is at `scripts/openai-docs-mcp.sh` and uses `curl` + `jq` against `https://developers.openai.com/mcp`. Subcommands: - `init`: initialize and inspect server capabilities. - `tools`: list available tools on the MCP server. - `search <query> [limit] [cursor]`: return JSON hits from the docs index. - `list [limit] [cursor]`: browse docs index. - `fetch <url> [anchor]`: return markdown for a doc page or section. - `endpoints`: list OpenAPI endpoints. - `openapi <endpoint-url> [lang1,lang2] [code-only]`: fetch OpenAPI schema or code samples. Environment: - `MCP_URL`: override the default MCP endpoint.
Excerpt, first 2,067 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit 31eb89d
git clone https://github.com/am-will/codex-skills git -C codex-skills checkout 31eb89d791f0
The author documents no install command, so this uses the repository directly. Our verdict covers commit 31eb89d791f0 only.
Works in which agents?
What its own text says, not a test
| Agent | Status | More |
|---|---|---|
| Codex | Mentioned in its text, not tested | Skills for Codex · About Codex |
| Cursor | Mentioned in its text, not tested | Skills for Cursor · About Cursor |
Audit history
Every audit, every source change
- !CAUTION B 89 / 100
first audit · source
31eb89d791f0
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/am-will/openai-docs-skill/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
All docs & writing skills →obra/superpowers
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions…
obra/superpowers
Use when you have a spec or requirements for a multi-step task, before touching code
obra/superpowers
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
Add this badge to your README
[](https://modelsatlas.com/skills/am-will/openai-docs-skill/)
<a href="https://modelsatlas.com/skills/am-will/openai-docs-skill/"><img src="https://modelsatlas.com/skills/am-will/openai-docs-skill/badge.svg" alt="ModelsAtlas: CAUTION B"></a>
Questions about openai-docs-skill
Is openai-docs-skill safe to install?
What can openai-docs-skill access on my machine?
Which assistants does openai-docs-skill work with?
How current is this page?
Sources
- github.com/am-will/codex-skills/tree/main/skills/openai-docs-ski — the audited source at commit 31eb89d791f0 and every finding aboveObserved · 27 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- Is openai-docs-skill safe to install?
- What can openai-docs-skill access on my machine?
- Which assistants does openai-docs-skill work with?