AA LESecureCl
LESecure Cloud Skills — encrypt or decrypt data using the LESecure API with layered locks (pin, password, MFA, time lock). Use this skill whenever the user mentions LESecure, LESecureCl, LESecure Cloud, layered encryption, multi-lock encryption, or wants to protect data with combinations of pin codes, passwords, phone-based MFA, or time-based access windows. Also trigger when the user wants to decrypt LESecure-encrypted data.
As a process A 84/100 · Runs to the end — weak spots: running it twice
How to improve
- 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
-
low Exfiltration
net-credential-useSKILL.md:28Credential used in a network call (verify the destination is the intended service) (documentation table row; documentation of a security skill)| `LESECURE_API_KEY` env var | Bearer token for the API. Must be set in the shell that runs `curl`; the skill never places it on the command line and never writes it to disk. | `[ -n "$LESECURE_API_KE
tablesecurity skill -
low Exfiltration
net-credential-useSKILL.md:183Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)1. **Preflight the requirements** from the Requirements section above. Specifically, confirm `$LESECURE_API_KEY` is set. If it is not set, show the user the one-time setup block and stop — do not proc
security skill
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens)
Process rating: all ten parameters 84/100
- 30Running it twice. 5 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 45 steps
- 100When it triggers. States when to use and when not to
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 7 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2907 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
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)
- +1No license
- +2Single-language instructions
- +3Description length 429: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 45 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.