AC drillr
Access Drillr's financial research capabilities — agentic search over company financials, a high-signal market event feed, published analyst articles, and persistent per-user watchlists. Use this whenever the user asks about stock prices, company fundamentals, earnings, SEC filings, market signals, sector trends, or wants to track tickers over time. Requires a user-specific API key obtainable at https://drillr.ai/developer/keys.
As a process C 63/100 · Has gaps — weak spots: result and completion, consistency, running it twice
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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Exfiltration
net-credential-useSKILL.md:195Credential used in a network call (verify the destination is the intended service)curl -H "Authorization: Bearer $DRILLR_API_KEY" \
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 63/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 23 mutating operations with no state check
- 40Consistency. Frontmatter name (drillr) differs from the folder (drillr-agent)
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4171 tokens
- 100Steps. 64 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Progress reporting. Reports progress
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 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
- +2Single-language instructions
- +3Description length 432: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 64 items
- +4Has examples (6 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.