AC key-guard
Security guardrail: prevents API keys from being sent to Claude. Triggers when user asks to call an external API, use a key, check credentials, read .env files, or view/edit scripts that may contain hardcoded keys. Always routes key usage through the local MCP server instead.
Security guardrail: prevents API keys from being sent to Claude.
As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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 · 4
✓ No critical or high findings
Medium and low: 4
-
low Exfiltration
read-dotenvREADME.md:44Reads a .env file (documentation of a security skill)cp .env.example .env
security skill -
low Exfiltration
read-dotenvSKILL.md:83Reads a .env file (documentation of a security skill)# Copy .env.example to .env and fill in your keys
security skill -
low Exfiltration
read-dotenvSKILL.md:84Reads a .env file (documentation of a security skill)cp .env.example .env
security skill
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 56/100
- 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
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 85Steps. 9 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1047 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 276: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.