BF pinchtab
Browser automation via HTTP API. Use for headless browser control, web automation, form filling, data extraction, and interactive element interaction. Supports launching instances, navigating pages, taking screenshots, extracting page structure, and clicking elements.
As a process F 28/100 · Will not run — References files that are not bundled: assets/google-screenshot.png
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 text references files that are not there: add them or drop the references.
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
medium Exfiltration
exfil-webhook-urlscripts/decode_screenshot.py:68Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)url = f"https://api.telegram.org/bot{bot_token}/sendPhoto"quoted -
medium Exfiltration
net-credential-usescripts/screenshot_and_send.sh:60Credential used in a network call (verify the destination is the intended service)TELE_RESPONSE=$(curl -s -X POST "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/sendPhoto" \ -
low Exfiltration
exfil-webhook-urlscripts/screenshot_and_send.sh:60Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)TELE_RESPONSE=$(curl -s -X POST "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/sendPhoto" \placeholder
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: assets/google-screenshot.png
Process rating: all ten parameters 28/100
- 0Tools and files. 1 referenced file(s) missing: assets/google-screenshot.png
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 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
- 40Consistency. Frontmatter name (pinchtab) differs from the folder (dexifried-pinchtab)
- 100Steps. 6 steps
- 100Execution cost. Instruction body is 505 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)
- +3Output format is not stated: the model decides each time
- -43 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 268: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 6 items
- +4Has examples (6 code blocks)
- +3All 6 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.