SKILLEMALL.ai
GitHub ↗ RU Sign in

DC agentcookie-install

Install agentcookie on a Mac source and a Linux or Mac sink so Chrome cookies sync continuously over Tailscale. Use when the user says "install agentcookie", "set up cookie sync", "share my Chrome sessions with my agent box", or "make my agent log in as me".

Not recommendedcritical or high security findings · low grade D
mvanhorn/agentcookie Agent Skills author: mvanhorn 2 files body ≈ 2 071 tokens Open the sourcegithub.com↗ analyzed 10 d ago

Install agentcookie on a Mac source and a Linux or Mac sink so Chrome cookies sync continuously over Tailscale.

As a process C 61/100 · Has gaps — weak spots: result and completion, consistency, running it twice

GeneratorGitHubAI and agentstype 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
72/100
safety, quality, tests
Safety 60%
62
Quality 40%
87
Run on models
none yet
Process rating
C
61/100
Has gaps
Result and completion w 14
0
Progress reporting w 2
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
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.

Dangerous commands 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 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.

For the author

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

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
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 · 5

  • high Exfiltration intent-browser-credential-store SKILL.md:11
    Accesses a browser credential / cookie store
    After install, the user does not touch agentcookie again. The source watches Chrome via fsnotify and pushes every cookie change to the sink within seconds. On Linux, the sink injects cookies via CDP i
Medium and low: 4
  • medium Dangerous commands cmd-privilege SKILL.md:51
    Privilege escalation / world-writable permissions
    sudo mv agentcookie /usr/local/bin/
  • medium Dangerous commands cmd-privilege SKILL.md:90
    Privilege escalation / world-writable permissions
    sudo mv agentcookie /usr/local/bin/
  • medium Exfiltration intent-browser-credential-store SKILL.md:201
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    The message `wrote 0 cookies` for Chrome SQLite is expected on Linux. Success is the live CDP inject line.
    quoted
  • medium Exfiltration intent-browser-credential-store SKILL.md:207
    Accesses a browser credential / cookie store (detector / deny-list definition)
    > Done. agentcookie is running on both `<source>` and `<sink>`. The source pushes cookies as soon as they change in Chrome. The sink injects them via CDP into Chrome at port 9223. browserUse, Puppetee
    detector

Files scanned: 2. 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 61/100

  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 2 mutating operations with no state check
  • 40Consistency. Frontmatter name (agentcookie-install) differs from the folder (skill)
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 11 steps
  • 100When it triggers. States when to use and when not to
  • 100Execution cost. Instruction body is 2071 tokens
  • low The response is described with custom markup (7 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

  • +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
  • +5Description quotes 4 example trigger phrases
  • +3Description length 258: enough signal without eating the budget
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 11 items
  • +4Has examples (12 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.