FD enable-chrome-gemini
Set up or repair Gemini in Chrome (Glic) on Windows, macOS, or Linux when enabling it for the first time outside the US or when the sidebar, floating panel, Alt+G shortcut, or top-bar entry disappears. Back up and patch Chrome Local State, restore region/eligibility fields, and check the required Glic flags and Chrome language.
Set up or repair Gemini in Chrome (Glic) on Windows, macOS, or Linux when enabling it for the first time outside the US or when the sidebar, floating panel…
As a process D 44/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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.
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
- 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.
- 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 · 8
-
high Exfiltration
intent-browser-credential-storeskill-card.md:17Accesses a browser credential / cookie storeDevelopers and technical users use this skill to guide setup or repair of Chrome Gemini/Glic by backing up and patching Chrome Local State, then checking the relevant flags and language settings.
-
high Exfiltration
intent-browser-credential-storeskill-card.md:25Accesses a browser credential / cookie storeRisk: The skill deliberately changes Chrome Local State to make Gemini/Glic appear eligible, including region fields and default language normalization.
-
high Exfiltration
intent-browser-credential-storeskill-card.md:45Accesses a browser credential / cookie store**Other Properties Related to Output:** [Produces Chrome Local State repair instructions, dry-run guidance, backup guidance, and platform-specific profile path handling.]
-
high Exfiltration
intent-browser-credential-storeSKILL.md:3Accesses a browser credential / cookie storedescription: Set up or repair Gemini in Chrome (Glic) on Windows, macOS, or Linux when enabling it for the first time outside the US or when the sidebar, floating panel, Alt+G shortcut, or top-bar ent
Medium and low: 4
-
medium Exfiltration
intent-browser-credential-storescripts/repair_chrome_gemini.py:2Accesses a browser credential / cookie store (quoted — discussed, not commanded)"""Enable or repair Chrome Gemini (Glic) eligibility state in Chrome's Local State."""
quoted -
medium Exfiltration
intent-browser-credential-storescripts/repair_chrome_gemini.py:200Accesses a browser credential / cookie store (detector / deny-list definition)description="Back up and repair Chrome Gemini eligibility in Local State for first-time setup or recovery on Windows, macOS, or Linux.",
detector -
medium Exfiltration
intent-browser-credential-storescripts/repair_chrome_gemini.py:205Accesses a browser credential / cookie store (quoted — discussed, not commanded)help="Chrome user data directory that contains Local State. Defaults to the current platform's Chrome profile location.",
quoted -
medium Exfiltration
intent-browser-credential-storescripts/repair_chrome_gemini.py:215Accesses a browser credential / cookie store (quoted — discussed, not commanded)help="Chrome UI language to normalize in Local State. Use an empty string to skip.",
quoted
Files scanned: 4. 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 44/100
- 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
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 85Steps. 35 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 812 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 329: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 35 items
- +4Has examples (2 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.