BC creem-agent
Autonomous full-time SaaS operations manager for Creem.io stores. Monitors heartbeat, handles failed payments, churn, revenue digests, and answers natural language queries.
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Broad scope
meta-agent-memory-dumptemplate/HEARTBEAT.mdAgent memory / workspace files bundled with the skill (4) — likely a workspace dump with personal data or tokenstemplate/HEARTBEAT.md, template/IDENTITY.md, template/SOUL.md, template/USER.md
-
low Exfiltration
net-credential-useSKILL.md:51Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)`curl -X POST https://api.creem.io/v1/discounts -H "x-api-key: $CREEM_API_KEY" -H "Content-Type: application/json" -d '{"name": "Winback: <email>", "code": "WINBACK_XXXXXX", "type": "percentage", "pervendor-hostquoted
Files scanned: 9. 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")
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 100Steps. 15 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 558 tokens
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)
- +4Structure: 2 headings, hard to scan
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 172: enough signal without eating the budget
- +3Step-by-step instructions: 15 items
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.