BF agent-email-inbox
Use when setting up an email inbox for an AI agent (Moltbot, Clawdbot, or similar) - configuring inbound email, webhooks, tunneling for local development, and implementing security measures to prevent prompt injection attacks.
Use when setting up an email inbox for an AI agent (Moltbot, Clawdbot, or similar) - configuring inbound email, webhooks, tunneling for local development, and…
As a process F 46/100 · Will not run — References files that are not bundled: ../send-email/references/installation.md
How to improve
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
low Exfiltration
read-dotenvSKILL.md:664Reads a .env file (documentation of a security skill)# with open('.env', 'a') as f:security skill
A further 3 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 10377 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: ../send-email/references/installation.md - note
frontmatter-keyunknown frontmatter key "inputs"
Process rating: all ten parameters 46/100
- 0Tools and files. 1 referenced file(s) missing: ../send-email/references/installation.md
- 0Result and completion. Does not say what the result is
- 30Running it twice. 58 mutating operations with no state check
- 40Execution cost. Instruction body is 10377 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 60Steps. 77 steps, 4 vague phrases
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 1 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 18 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)
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 226: enough signal without eating the budget
- +4Structure: 67 headings
- +3Step-by-step instructions: 77 items
- +4Has examples (28 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.