BD wordpress-selfhosted
Manage a self-hosted WordPress site via SSH+WP-CLI (primary) and WP REST API (when direct HTTPS access is available). Use when asked to write, draft, publish, update, or delete posts/pages on a self-hosted WordPress installation — including SEO optimization, categories/tags, featured images, author assignment, and proper post formatting. Designed for WordPress running on LXC, VPS, or bare-metal (not WordPress.com hosted). Requires: ssh, scp, curl, jq, wp (WP-CLI). Optional: op (1Password CLI for credential hydration via SSH agent socket). Network: SSH to user-configured WordPress host (LAN IP or public domain). Credentials: SSH key (via ssh-agent or 1Password SSH agent on macOS), WP application password (stored in 1Password, item name configurable via WP_1P_ITEM). Required env vars (gated; set via openclaw.json skills.entries or shell environment): WP_HOST, WP_SSH_USER, WP_ROOT. Optional config (TOOLS.md or env): WP_USER, WP_1P_ITEM. File writes: /tmp/post-content.html, /tmp/*.html (temporary content files SCP'd to host, created mode 600, cleaned up after use). Uses -o StrictHostKeyChecking=accept-new for SSH by default (trust-on-first-use); see Security Notes for alternatives.
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Shorten the description to 1024 characters.
- 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 · 5
✓ No critical or high findings
Medium and low: 5
-
low Exfiltration
net-credential-useSKILL.md:96Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl -s -u "$WP_USER:$WP_PASS" "$WP_BASE/users/me" | jq '{id, name}'security skill -
low Exfiltration
net-credential-useSKILL.md:99Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl -s -u "$WP_USER:$WP_PASS" "$WP_BASE/posts?per_page=20&status=any" | jq '[.[] | {id, title: .title.rendered, status}]'security skill -
low Exfiltration
net-credential-useSKILL.md:102Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl -s -u "$WP_USER:$WP_PASS" "$WP_BASE/posts/<ID>?context=edit" | jq -r '.content.raw'
security skill -
low Exfiltration
net-credential-useSKILL.md:105Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl -s -X POST -u "$WP_USER:$WP_PASS" "$WP_BASE/posts" \
security skill -
low Exfiltration
net-credential-useSKILL.md:110Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl -s -X POST -u "$WP_USER:$WP_PASS" "$WP_BASE/posts/<ID>" \
security skill
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1196 chars, limit 1024
Process rating: all ten parameters 43/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 7 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 24 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2605 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 1196: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 18 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (14 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.