BC signalradar
SignalRadar — Monitor Polymarket prediction markets for probability changes and send alerts when thresholds are crossed. Use when user asks to "add a Polymarket market", "monitor Polymarket", "check prediction markets", "list my monitors", "remove a monitor", "track market probabilities", "run market check", "check schedule status", "change threshold", "change check frequency", "health check", "find markets about X", "search prediction markets", "trending markets", "what is the market pricing for X", or sends a polymarket.com URL asking to add, check, or learn about a market. When user shares a polymarket.com URL without explicit intent, use `show` to display market info — do NOT auto-add. Do NOT use for stock/crypto trading signals, sports betting, price prediction models, or general financial analysis.
As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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 · 10
✓ No critical or high findings
Medium and low: 10
-
medium Exfiltration
exfil-webhook-urlscripts/signalradar.py:3949Webhook / callback URL commonly used for exfiltration (verify the destination) (detector / deny-list definition)"slack": "https://hooks.slack.com/services/YOUR/WEBHOOK/URL",
detector -
medium Exfiltration
exfil-webhook-urlscripts/signalradar.py:3950Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)"discord": "https://discord.com/api/webhooks/YOUR/WEBHOOK/URL",
quoted -
medium Dangerous commands
cmd-autorun-instructionSKILL.md:189Instructs the agent to auto-run a script on every sessionWhen user asks about current settings, ALWAYS run `signalradar.py config` first. Do NOT guess or recall from memory. If a value is missing, report the default and state "this is the default value".
-
low Exfiltration
exfil-webhook-urlconfig.example.json:17Webhook / callback URL commonly used for exfiltration (verify the destination) (detector / deny-list definition; security demo / example; test fixture / example file)"target": "https://hooks.slack.com/services/YOUR/WEBHOOK/URL"
detectordemofixture -
low Exfiltration
exfil-webhook-urlreferences/config.md:206Webhook / callback URL commonly used for exfiltration (verify the destination) (detector / deny-list definition; security demo / example)"target": "https://hooks.slack.com/services/YOUR/WEBHOOK/URL"
detectordemo -
low Exfiltration
exfil-webhook-urlreferences/config.md:219Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)"target": "https://api.telegram.org/bot<TOKEN>/sendMessage?chat_id=<CHAT_ID>"
placeholder -
low Exfiltration
exfil-webhook-urlreferences/config.md:232Webhook / callback URL commonly used for exfiltration (verify the destination) (detector / deny-list definition; security demo / example)"target": "https://discord.com/api/webhooks/YOUR/WEBHOOK/URL"
detectordemo -
low Dangerous commands
cmd-cron-mentionreferences/config.md:290Mentions editing / listing crontab (detector / deny-list definition)⚠️ **Enabling monitoring changes your system, not just this skill's config.** It adds a tagged entry to your user `crontab` (or a job to `openclaw cron`) that keeps running after the session ends and
detector -
low Exfiltration
exfil-webhook-urlscripts/signalradar.py:3948Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)"telegram": "https://api.telegram.org/bot<TOKEN>/sendMessage?chat_id=<CHAT_ID>",
placeholder -
low Dangerous commands
cmd-cron-mentionSKILL.md:105Mentions editing / listing crontabcrontab -l | grep signalradar # see exactly what was installed
Files scanned: 17. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 8782 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 63/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 38 mutating operations with no state check
- 40Execution cost. Instruction body is 8782 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 84 steps
- 100Failures and branches. 10 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 15 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (12 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
- +3Description length 815: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -38 of 9 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +5Description quotes 15 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 36 headings
- +3Step-by-step instructions: 84 items
- +4Has examples (14 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.