SKILLEMALL.ai
GitHub ↗ RU Sign in

FC wordpress-mcp

Use when exposing a WordPress site to AI agents via MCP, or when WordPress MCP setup fails.

ClawHub Agent Skills author: Afonso Dutra Nogueira Filho v1.0.6 MIT-0 12 files · 3 scripts body ≈ 9 974 tokens Open the sourceclawhub.ai↗ analyzed 6 d ago

Expose WordPress to AI agents over MCP.

As a process C 61/100 · Has gaps — weak spots: result and completion, execution cost, running it twice

IntegrationWordPressGitHubAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
F
32/100
safety, quality, tests
Safety 60%
0
Quality 40%
79
Run on models
none yet
Process rating
C
61/100
Has gaps
Result and completion w 14
0
Running it twice w 4
30
Execution cost w 6
40
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 24

✓ No critical or high findings

Medium and low: 24
  • medium Dangerous commands cmd-privilege references/mcp-adapter-guide.md:43
    Privilege escalation / world-writable permissions
    sudo cp -r /tmp/mcp-adapter-extract/mcp-adapter $WP_PATH/wp-content/plugins/mcp-adapter
  • medium Dangerous commands cmd-privilege references/mcp-adapter-guide.md:44
    Privilege escalation / world-writable permissions
    sudo chown -R www:www $WP_PATH/wp-content/plugins/mcp-adapter
  • medium Dangerous commands cmd-privilege references/mcp-adapter-guide.md:82
    Privilege escalation / world-writable permissions
    sudo chown -R www:www $WP_PATH/wp-content/plugins/mcp-adapter
  • medium Dangerous commands cmd-privilege references/mcp-adapter-guide.md:106
    Privilege escalation / world-writable permissions
    sudo tee $WP_PATH/wp-content/mu-plugins/enable-app-passwords.php > /dev/null <<'EOF'
  • medium Dangerous commands cmd-privilege references/real-world-workflows.md:111
    Privilege escalation / world-writable permissions
    sudo cp -r /tmp/blocksy-extract/blocksy $WP_PATH/wp-content/themes/blocksy
  • medium Dangerous commands cmd-privilege references/real-world-workflows.md:112
    Privilege escalation / world-writable permissions
    sudo chown -R www:www $WP_PATH/wp-content/themes/blocksy
  • medium Dangerous commands cmd-privilege references/real-world-workflows.md:171
    Privilege escalation / world-writable permissions
    sudo cp /tmp/myimage.png $UPLOAD_DIR/myimage.png
  • medium Dangerous commands cmd-privilege references/real-world-workflows.md:172
    Privilege escalation / world-writable permissions
    sudo chown www:www $UPLOAD_DIR/myimage.png
  • medium Dangerous commands cmd-privilege references/real-world-workflows.md:173
    Privilege escalation / world-writable permissions
    sudo chmod 644 $UPLOAD_DIR/myimage.png
  • medium Dangerous commands cmd-privilege references/troubleshooting.md:121
    Privilege escalation / world-writable permissions
    sudo tee $WP_PATH/wp-content/mu-plugins/enable-app-passwords.php > /dev/null <<'EOF'
  • medium Dangerous commands cmd-privilege references/troubleshooting.md:174
    Privilege escalation / world-writable permissions
    sudo cp "$FILE" "$FILE.bak"
  • medium Dangerous commands cmd-privilege references/troubleshooting.md:177
    Privilege escalation / world-writable permissions
    sudo python3 <<'PY'
  • medium Dangerous commands cmd-privilege references/troubleshooting.md:257
    Privilege escalation / world-writable permissions
    sudo cp -r ai-engine $WP_PATH/wp-content/plugins/
  • medium Dangerous commands cmd-privilege references/troubleshooting.md:258
    Privilege escalation / world-writable permissions
    sudo chown -R www:www $WP_PATH/wp-content/plugins/ai-engine
  • medium Dangerous commands cmd-privilege scripts/install_wp_plugin.sh:175
    Privilege escalation / world-writable permissions
    $SUDO rm -rf "$PLUGINS_DIR/mcp-adapter"
  • medium Dangerous commands cmd-privilege scripts/install_wp_plugin.sh:176
    Privilege escalation / world-writable permissions
    $SUDO cp -r "$SRC" "$PLUGINS_DIR/mcp-adapter"
  • medium Dangerous commands cmd-privilege scripts/install_wp_plugin.sh:177
    Privilege escalation / world-writable permissions
    $SUDO chown -R "${WEB_USER}:${WEB_USER}" "$PLUGINS_DIR/mcp-adapter"
  • medium Dangerous commands cmd-privilege scripts/install_wp_plugin.sh:184
    Privilege escalation / world-writable permissions
    $SUDO chown -R "${WEB_USER}:${WEB_USER}" "$PLUGINS_DIR/mcp-adapter" 2>/dev/null || true
  • medium Dangerous commands cmd-privilege scripts/install_wp_plugin.sh:223
    Privilege escalation / world-writable permissions
    $SUDO cp -r "$TMPDIR/extract/ai-engine" "$PLUGINS_DIR/ai-engine"
  • medium Dangerous commands cmd-privilege SKILL.md:696
    Privilege escalation / world-writable permissions
    sudo cp -r /tmp/blocksy-extract/blocksy $WP_PATH/wp-content/themes/blocksy
  • medium Dangerous commands cmd-privilege SKILL.md:697
    Privilege escalation / world-writable permissions
    sudo chown -R www:www $WP_PATH/wp-content/themes/blocksy
  • medium Dangerous commands cmd-privilege SKILL.md:717
    Privilege escalation / world-writable permissions
    sudo cp /tmp/image.png $WP_PATH/wp-content/uploads/2026/09/image.png
  • medium Dangerous commands cmd-privilege SKILL.md:718
    Privilege escalation / world-writable permissions
    sudo chown www:www $WP_PATH/wp-content/uploads/2026/09/image.png
  • low Risky intent intent-offensive-security SKILL.md:38
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    > - **Do not run `sudo` or `wp eval` automatically**: privilege escalation and arbitrary code execution require justification and confirmation.

Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 9974 tokens (recommended < 5000); move details to references/
  • note edit-residue the text marks something as outdated (lines 6, 31, 91, 745, 760): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 61/100

  • 0Result and completion. Does not say what the result is
  • 30Running it twice. 38 mutating operations with no state check
  • 40Execution cost. Instruction body is 9974 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, web, git) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 55 steps, 1 vague phrases
  • 100Failures and branches. 2 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 22 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (6 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 91: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +4Structure: 47 headings
  • +3Step-by-step instructions: 55 items
  • +4Has examples (34 code blocks)
  • +4Reference files are cited in the instructions (7 of 7)
  • +3All 3 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.

External checks

ClawHub: suspicious
The skill has a coherent WordPress MCP setup purpose, but its scripts and references handle credentials, agent configuration, and remote plugin installs in ways that require careful review before use.
LLM: suspicious (high) · 16 Sept 2026