AC camofox-cloaked-browser
Use Camofox/Camoufox as an opt-in anti-detection browser server for agent workflows that need cloaked browsing. Covers npm/npx startup, OpenClaw plugin tools, REST API commands, session/tab workflow, environment variables, process-scoped CAMOFOX_URL for Hermes, and hard rules such as always sending userId and re-snapshotting after state-changing actions. Do not use for normal web search, text extraction, curl fetches, or ordinary browser automation.
Use Camofox/Camoufox as an opt-in anti-detection browser server for agent workflows that need cloaked browsing.
As a process C 60/100 · Has gaps — weak spots: inputs and preconditions, running it twice, progress reporting
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Exfiltration
net-credential-useSKILL.md:238Credential used in a network call (verify the destination is the intended service) (security demo / example; quoted — discussed, not commanded)-d "{\"userId\":\"$USER_ID\",\"sessionKey\":\"$SESSION_KEY\",\"url\":\"https://example.com\"}" \demoquoted
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 453 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - note
edit-residuethe text marks something as outdated (lines 369): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 60/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 60Consistency. The Hermes dialect needs category and tags
- 85Steps. 105 steps, 1 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 3834 tokens
- low 11 top-level sections: this looks like several domains in one skill
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
- -2localhost URLs: will not work for another user
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 453: enough signal without eating the budget
- +4Structure: 33 headings
- +3Step-by-step instructions: 105 items
- +3Output format is stated explicitly
- +4Has examples (33 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.