Live survey286 models · 13 providers · 19,992 auditsAudited verification-before-completion · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

apex

skill · oracle/skillsUPL-1.0 licenceAudited 20 Oct 2026 · source 1d5e869fce7a

★ 897pushed 11 days ago
✕BLOCKGrade D · 69/100 · 19 findings · 1d5e869
897repo stars · whole oracle/skills
Read the findingsView source on GitHub ↗

Is it safe? No — BLOCK, grade D (69/100). We read this skill's source at commit 1d5e869fce7a and observed filesystem and shell access and no hard-coded secrets. The audit raised 19 findings, 2 critical or high. What it does: Oracle APEX skills for Oracle APEX application development.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
CoCopilotAIGoogle AI Mode
Cite

Cite this page

ModelsAtlas. “apex (oracle/skills)”. Retrieved 20 Oct 2026. https://modelsatlas.com/skills/oracle/apex

Blocked. The page stays public so you can check this skill if someone recommended it to you. The audit found 2 critical or high findings, starting with “Prompt injection” in apexlang/26.1/apexlang-inventory/SKILL.md:422. Do not install it without reading them.

Trust audit

Audit 0.4.1 · source read 20 Oct 2026

Trust score69/100✕BLOCK D
0 critical2 high0 medium12 low5 info

BLOCK means the audit found something that could harm you or your machine. Grade D is shared by 642 of 14,816 audited skills.

What the source does

  • FilesystemDeclared5 observations
  • NetworkNone observedNo outbound calls in the source
  • ShellDeclared5 observations
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS8
L1 Static sourceSecrets, path traversal, supply chain, hidden codePASS3
L2 InstructionsPrompt injection, authority framing, hidden directivesFAIL8
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (19)

HIGHPrompt injectionprompt.credential_read · apexlang/26.1/apexlang-inventory/SKILL.md:422
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
- [plugin-variants/openDoorCredentials](assets/app/authentication/plugin-variants/open-door-credentials/open-door-credentials.md) — Enables anyone to access your application. Enter any identifier that
Why
asks the agent to read credentials
Fix
—
HIGHPrompt injectionprompt.credential_read · apexlang/26.2/apexlang-inventory/SKILL.md:422
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
- [plugin-variants/openDoorCredentials](assets/app/authentication/plugin-variants/open-door-credentials/open-door-credentials.md) — Enables anyone to access your application. Enter any identifier that
Why
asks the agent to read credentials
Fix
—
LOWInventory / provenanceinv.suspicious_name · apexlang/26.1/apexlang-inventory/assets/app/page/process/parameter-c2/parameter-c2.md
F-13 Inventory / provenanceCWE-1104Layer L0
parameter-c2.md
Why
member named after an attack tool
Fix
remove or justify
LOWInventory / provenanceinv.suspicious_name · apexlang/26.1/apexlang-inventory/assets/app/page/region/action-c2/action-c2.md
F-13 Inventory / provenanceCWE-1104Layer L0
action-c2.md
Why
member named after an attack tool
Fix
remove or justify
LOWInventory / provenanceinv.suspicious_name · apexlang/26.1/apexlang-inventory/assets/app/page/region/column-c2/column-c2.md
F-13 Inventory / provenanceCWE-1104Layer L0
column-c2.md
Why
member named after an attack tool
Fix
remove or justify
LOWInventory / provenanceinv.suspicious_name · apexlang/26.1/apexlang-inventory/assets/app/page/region/column-group-c2/column-group-c2.md
F-13 Inventory / provenanceCWE-1104Layer L0
column-group-c2.md
Why
member named after an attack tool
Fix
remove or justify
LOWInventory / provenanceinv.suspicious_name · apexlang/26.1/apexlang-inventory/assets/app/page/region/saved-report-c2/saved-report-c2.md
F-13 Inventory / provenanceCWE-1104Layer L0
saved-report-c2.md
Why
member named after an attack tool
Fix
remove or justify
LOWFilesystem / pathfs.traversal · apexlang/26.1/apexlang-generation/runtime/grammar_contract.mjs:94
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
const repoRoot = path.resolve(moduleDir, "../../../..");
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · apexlang/26.1/apexlang-generation/runtime/lib/common.mjs:54
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
rootPath: path.resolve(MODULE_DIR, "../../../..")
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · apexlang/26.1/apexlang-generation/tools/compiler-truth-audit.mjs:17
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
: path.resolve(path.dirname(SCRIPT_PATH), "../../..");
Why
No further detail recorded for this rule.
Fix
—
LOWPrompt injectionprompt.authority_framing · apexlang/26.1/apexlang-inventory/SKILL.md:422
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
- [plugin-variants/openDoorCredentials](assets/app/authentication/plugin-variants/open-door-credentials/open-door-credentials.md) — Enables anyone to access your application. Enter any identifier that
Why
No further detail recorded for this rule.
Fix
—
LOWPrompt injectionprompt.authority_framing · apexlang/26.2/apexlang-inventory/SKILL.md:422
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
- [plugin-variants/openDoorCredentials](assets/app/authentication/plugin-variants/open-door-credentials/open-door-credentials.md) — Enables anyone to access your application. Enter any identifier that
Why
No further detail recorded for this rule.
Fix
—
LOWPrompt injectionprompt.credential_read · apexlang/26.2/apexlang-inventory/assets/app/authentication/authentication.md:12
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
- `type` — `<STRING>`; —; Yes; —; `<enum:[custom:"Custom", custom:"Custom", databaseAccounts:"Database Accounts", databaseAccounts:"Database Accounts", httpHeaderVariable:"HTTP Header Variable", httpH
Why
asks the agent to read credentials
Fix
—
LOWPrompt injectionprompt.transfer_instruction · apexlang/26.2/apexlang-inventory/assets/app/rest-data-source/operation/operation.md:42
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
- `caching` — `<STRING>`; Select how the Oracle APEX engine can cache REST Source responses on the server side. If caching can be used, the component will be rendered based on cached results instead o
Why
an instruction to move sensitive data to an outside destination
Fix
remove; a skill never needs the user's secrets off the machine
INFOInventory / provenanceinv.oversize · apexlang/26.1/apexlang-generation/assets/grammar/apexlang.ebnf
F-13 Inventory / provenanceCWE-1104Layer L0
apexlang/26.1/apexlang-generation/assets/grammar/apexlang.ebnf
Why
1140533 bytes not read
Fix
—
INFOInventory / provenanceinv.oversize · apexlang/26.1/apexlang-inventory/assets/app/page/region/series/series.md
F-13 Inventory / provenanceCWE-1104Layer L0
apexlang/26.1/apexlang-inventory/assets/app/page/region/series/series.md
Why
2565436 bytes not read
Fix
—
INFOInventory / provenanceinv.oversize · apexlang/26.2/apexlang-inventory/assets/app/page/region/series/series.md
F-13 Inventory / provenanceCWE-1104Layer L0
apexlang/26.2/apexlang-inventory/assets/app/page/region/series/series.md
Why
2565435 bytes not read
Fix
—
INFOPrompt injectionprompt.credential_read · apexlang/26.1/apexlang-inventory/assets/app/authentication/authentication.md:12
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
- `type` — `<STRING>`; —; Yes; —; `<enum:[custom:"Custom", custom:"Custom", databaseAccounts:"Database Accounts", databaseAccounts:"Database Accounts", httpHeaderVariable:"HTTP Header Variable", httpH
Why
asks the agent to read credentials
Fix
—
INFOPrompt injectionprompt.credential_read · apexlang/26.1/apexlang-inventory/assets/app/authentication/plugin-variants/open-door-credentials/open-door-credentials.md:11
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
- `type` — `<STRING>`; —; Yes; —; `<enum:[openDoorCredentials:"Open Door Credentials"]>`; —; —;
Why
asks the agent to read credentials
Fix
—

Audit 0.4.1 · source sha 1d5e869fce7a · 20 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisheroracle GitHub organizationOwner of the repository this skill is read from
  • Source folderoracle/skills/apexThe exact folder we audited
  • LicenceUPL-1.0As the repository states it
  • Commit pinned for this verdict1d5e869fce7aA new audit runs when the source changes
  • Repository statusNot archivedLast push 11 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Oracle APEX skills for Oracle APEX application development.

---
name: apex
description: Oracle APEX skills for Oracle APEX application development.
---

# APEXLang Skills

This domain contains Oracle APEX skills for Oracle APEX application development.

## How to Use This Domain

1. Start with the routing table below.
2. For APEXlang work, open `apex/apexlang/SKILL.md` and route to the matching APEX version.
3. Read only the specific file or category you need.

## Directory Structure

```text
apex/
└── apexlang/
    ├── SKILL.md
    ├── 26.1/
    │   ├── SKILL.md
    │   ├── apexlang-generation/
    │   ├── apexlang-compile/
    │   ├── apexlang-deploy/
    │   ├── apexlang-inventory/
    │   └── apexlang-example-applications/
    └── 26.2/
        ├── SKILL.md
        ├── apexlang-compile/
        ├── apexlang-deploy/
        ├── apexlang-inventory/
        └── apexlang-example-applications/
```

## Category Routing


| Topic                                          | Directory            |
| ---------------------------------------------- | -------------------- |
| APEXlang version router                        | `apex/apexlang`      |
| APEXlang skills for APEX 26.1                  | `apex/apexlang/26.1` |
| APEXlang skills for APEX 26.2                  | `apex/apexlang/26.2` |


## Key Starting Points

- `apex/apexlang/SKILL.md`
- `apex/apexlang/26.1/SKILL.md`
- `apex/apexlang/26.2/SKILL.md`
- `apex/apexlang/26.1/apexlang-generation/references/workflows/apex-generation.md`
- `apex/apexlang/26.1/apexlang-generation/references/domains/README.md`

Excerpt, first 1,514 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 1d5e869

git clone https://github.com/oracle/skills
git -C skills checkout 1d5e869fce7a

The author documents no install command, so this uses the repository directly. Our verdict covers commit 1d5e869fce7a only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
CodexMentioned in its text, not testedSkills for Codex · About Codex
CursorMentioned in its text, not testedSkills for Cursor · About Cursor
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. ✕BLOCK D 69 / 100

    first audit · source 1d5e869fce7a

Similar skills

Docker Patterns✕BLOCK

affaan-m/ECC

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration. Use when setting up containerized development environments or reviewing…

★ 263kGrade D
loom-transcript✕BLOCK

n8n-io/n8n

Fetch and display the full transcript from a Loom video URL. Use when the user wants to get or read a Loom transcript.

★ 208kGrade D
claude-api✕BLOCK

anthropics/skills

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it…

★ 177kGrade D

Questions about apex

What does the apex skill do?
Oracle Skills is a curated, open-source collection of practical, installable skills for working with Oracle technologies. It provides developers, administrators, and AI agents with high-quality, source-backed guidance across the entire Oracle ecosystem.
Is apex safe to install?
No — not without reading the findings first. The audit graded it D (69/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What can apex access on my machine?
The audit observed that it runs shell commands and reads or writes files. Each of those is consistent with what it says it does. Secrets in the source: none found.
Which assistants does apex work with?
Its documentation mentions codex and cursor. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (1d5e869fce7a), read on 2026-10-20. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

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.