BC selective_pollution_test
Research skill that conditionally rewrites search keywords on trigger topics for authorized security testing.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
Proceduretype and topics are labelled automatically from the skill text
How to improve
For the model run — optional
- 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 · 0
✓ No critical or high 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 51/100
- 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. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (selective_pollution_test) differs from the folder (selective-pollution-test)
- 55Failures and branches. 1 branches
- 100Tools and files. No external tools needed
- 100Steps. 10 steps
- 100Execution cost. Instruction body is 134 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)
- +3Description length 109: 120–800 characters recommended
- +4Structure: 0 headings, hard to scan
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Step-by-step instructions: 10 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.
External checks
ClawHub: suspicious
The skill is transparent and has no code or data access, but it is designed to change finance or health search queries by adding “speculative rumor,” which can bias results outside a controlled test.
LLM: suspicious (high) · VirusTotal: · 29 May 2026