SKILLEMALL.ai
GitHub ↗ RU Sign in

DC browse

Drive a real stealth browser from your shell — act on websites (order food, file an expense, pull data behind a login), with per-person persistent sign-ins kept in the person's browser profile (Kernel, Anchor, Browserbase, or Browser Use — picked by which API key you have). Use for ACTING on a site; to just read a page, use curl/wget first. Requires managed model access and a keychain grant for the browser provider key; follow the missing-key steps below.

yc-software/qm Agent Skills author: yc-software MIT 5 files body ≈ 4 173 tokens Open the sourcegithub.com↗ analyzed 9 h ago

Drive a real stealth browser from your shell — act on websites (order food, file an expense, pull data behind a login), with per-person persistent sign-ins…

As a process C 63/100 · Has gaps — weak spots: result and completion

IntegrationData and analyticstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
D
67/100
safety, quality, tests
Safety 60%
55
Quality 40%
84
Run on models
none yet
Process rating
C
63/100
Has gaps
Result and completion w 14
0
When it triggers w 12
50
Failures and branches w 10
50
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

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".

For the author

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

    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 · 9

    ✓ No critical or high findings

    Medium and low: 9
    • medium Exfiltration net-credential-use providers/anchor.md:71
      Credential used in a network call (verify the destination is the intended service)
      curl -fsS -X DELETE "https://api.anchorbrowser.io/v1/sessions/$ANCHOR_SID" -H "anchor-api-key: $ANCHOR_API_KEY"
    • medium Exfiltration net-credential-use providers/anchor.md:88
      Credential used in a network call (verify the destination is the intended service)
      curl -fsS -X DELETE "https://api.anchorbrowser.io/v1/sessions/$SIGNIN_SID" -H "anchor-api-key: $ANCHOR_API_KEY"
    • medium Exfiltration net-credential-use providers/anchor.md:119
      Credential used in a network call (verify the destination is the intended service)
      curl -fsS -X DELETE "https://api.anchorbrowser.io/v1/sessions/$ANCHOR_SID" -H "anchor-api-key: $ANCHOR_API_KEY"
    • medium Exfiltration net-credential-use providers/kernel.md:33
      Credential used in a network call (verify the destination is the intended service)
      curl -fsS -X "$1" "https://api.onkernel.com$2" -H "Authorization: Bearer $KERNEL_API_KEY" \
    • medium Exfiltration net-credential-use providers/kernel.md:36
      Credential used in a network call (verify the destination is the intended service)
      curl -fsS -X "$1" "https://api.onkernel.com$2" -H "Authorization: Bearer $KERNEL_API_KEY"
    • medium Exfiltration net-credential-use providers/kernel.md:129
      Credential used in a network call (verify the destination is the intended service)
      curl -fsS -X POST "$AGENT_API_URL/v1/keychain/credentials" -H "x-agent-capability: $AGENT_API_TOKEN" \
    • medium Exfiltration net-credential-use SKILL.md:103
      Credential used in a network call (verify the destination is the intended service)
      curl -fsS "$AGENT_API_URL/v1/keychain/credentials" -H "x-agent-capability: $AGENT_API_TOKEN"
    • medium Exfiltration net-credential-use SKILL.md:122
      Credential used in a network call (verify the destination is the intended service)
      curl -fsS "$AGENT_API_URL/v1/keychain/credentials" -H "x-agent-capability: $AGENT_API_TOKEN" \
    • medium Exfiltration net-credential-use SKILL.md:140
      Credential used in a network call (verify the destination is the intended service)
      curl -fsS -X POST "$AGENT_API_URL/v1/keychain/credentials" -H "x-agent-capability: $AGENT_API_TOKEN" \

    Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 63/100

    • 0Result and completion. Does not say what the result is
    • 50When it triggers. No condition that starts the skill
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 70Execution cost. Instruction body is 4173 tokens
    • 100Steps. 18 steps
    • 100Consistency. Name and required fields are in place
    • 100Running it twice. Mutating operations check current state
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • high The skill tells the model to perform an irreversible action with no human approval

    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
    • +1No license
    • +2Single-language instructions
    • +3Description length 459: enough signal without eating the budget
    • +4Structure: 7 headings
    • +3Step-by-step instructions: 18 items
    • +4Has examples (7 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.