CC ibkr-httpapi
HTTP+JSON control plane over Interactive Brokers (ib_async + a local IB Gateway container) that the user already runs. Talk to a real brokerage with curl + JSON — market data (OHLC bars, snapshot/historical ticks, option chains + Greeks) across stocks/options/futures/cfd/forex/crypto, account/positions summaries, order placement / retrieval / cancellation, and server-side technical analysis via the wickworks sidecar. Bearer-token auth (API_TOKEN). Use when the user has deployed ibkr-httpapi and set IBKR_HTTPAPI_URL and wants to pull IBKR market data, inspect account/positions, run TA, or place/cancel orders. THIS API CAN PLACE, EXERCISE, AND CANCEL REAL ORDERS ON A REAL IBKR ACCOUNT — every account-mutating call requires explicit per-action user confirmation.
HTTP+JSON control plane over Interactive Brokers (ibasync + a local IB Gateway container) that the user already runs.
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, 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
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 7
✓ No critical or high findings
Medium and low: 7
-
medium Exfiltration
net-credential-usereferences/setup.md:40Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer $API_TOKEN" http://loca…889/v1/ping
-
medium Exfiltration
net-credential-useSKILL.md:183Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer $API_TOKEN" "$IBKR_HTTPAPI_URL/ping"
-
medium Exfiltration
net-credential-useSKILL.md:297Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer $API_TOKEN" \
-
medium Exfiltration
net-credential-useSKILL.md:300Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer $API_TOKEN" \
-
medium Exfiltration
net-credential-useSKILL.md:303Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer $API_TOKEN" \
-
medium Exfiltration
net-credential-useSKILL.md:306Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer $API_TOKEN" \
-
low Risky intent
intent-offensive-securitySKILL.md:80Offensive-security / dual-use content (legitimate for authorised testing; review intended use)3. **No credential harvesting.** Read the token only from the `API_TOKEN`
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7619 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 61/100
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 19 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 7619 tokens
- 85Steps. 41 steps, 2 vague phrases
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (36 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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 769: enough signal without eating the budget
- +4Structure: 37 headings
- +3Step-by-step instructions: 41 items
- +4Has examples (12 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.