CF agent4-io
Build and run grounded business agents on agent4.io over MCP — agents, knowledge bases, load-on-demand skills, stateful Storylines and page playbooks.
Build and run grounded business agents on agent4.io over MCP — agents, knowledge bases, load-on-demand skills, stateful Storylines and page playbooks.
As a process F 43/100 · Will not run — References files that are not bundled: /cookbook/build-a-knowledge-base, /cookbook/create-a-skill, /cookbook/connect-your-mcp-server
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
medium Exfiltration
net-credential-useSKILL.md:330Credential used in a network call (verify the destination is the intended service)curl -s "https://api.telegram.org/bot$BOT_TOKEN/setMyCommands" -H "Content-Type: application/json" -d '{ -
medium Exfiltration
net-credential-useSKILL.md:796Credential used in a network call (verify the destination is the intended service)curl -X POST $BASE/mcp-servers -H "X-API-Key: $KEY" -H 'Content-Type: application/json' \
-
low Exfiltration
exfil-webhook-urlSKILL.md:330Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)curl -s "https://api.telegram.org/bot$BOT_TOKEN/setMyCommands" -H "Content-Type: application/json" -d '{placeholder
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 26121 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: /cookbook/build-a-knowledge-base - warning
missing-refreference to a missing file: /cookbook/create-a-skill - warning
missing-refreference to a missing file: /cookbook/connect-your-mcp-server - warning
missing-refreference to a missing file: /cookbook/build-a-storyline - warning
missing-refreference to a missing file: /cookbook/configure-page-playbooks - warning
missing-refreference to a missing file: /cookbook/create-support-agent - warning
missing-refreference to a missing file: /cookbook/design-principles - warning
missing-refreference to a missing file: /concepts/playbooks - warning
missing-refreference to a missing file: /cookbook/charts-in-answers - note
frontmatter-keyunknown frontmatter key "homepage" - note
edit-residuethe text marks something as outdated (lines 324, 1699, 1700): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 43/100
- 0Tools and files. 9 referenced file(s) missing: /cookbook/build-a-knowledge-base, /cookbook/create-a-skill, /cookbook/connect-your-mcp-server
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 10Execution cost. Instruction body is 26121 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 85Steps. 72 steps, 1 vague phrases
- 100Failures and branches. 7 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 59 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (19 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 150: enough signal without eating the budget
- +4Structure: 70 headings
- +3Step-by-step instructions: 72 items
- +4Has examples (51 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 49.