FC clash-auto-switch
(no description)
As a process C 51/100 · Has gaps — 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 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.
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.
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
- 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.
- Add a description to the frontmatter: without it the skill never triggers.
- 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 Dangerous commands
cmd-persistenceREADME.md:164Persistence mechanism (cron / launchd / scheduled task / autorun registry)Register-ScheduledTask -TaskName "ClashAutoSwitch" -Trigger (New-ScheduledTaskTrigger -Once -At (Get-Date) -RepetitionInterval (New-TimeSpan -Minutes 15)) -Action (New-ScheduledTaskAction -Execute "py
Medium and low: 7
-
medium Exfiltration
net-credential-useclash-switch-v2.sh:83Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer ${CLASH_SECRET}" "${CLASH_API}/proxies" | jq -r '.proxies | keys[]' 2>/dev/null | grep -v "^GLOBAL$\|^ DIRECT$\|^REJECT$\|^PROXY$" -
medium Exfiltration
net-credential-useclash-switch-v2.sh:88Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer ${CLASH_SECRET}" "${CLASH_API}/proxies/ChatGPT" | jq -r '.now' 2>/dev/null -
medium Exfiltration
net-credential-useclash-switch-v2.sh:94Credential used in a network call (verify the destination is the intended service)curl -s -X PUT -H "Authorization: Bearer ${CLASH_SECRET}" \ -
medium Exfiltration
net-credential-useclash-switch-v2.sh:104Credential used in a network call (verify the destination is the intended service)local delay=$(curl -s -H "Authorization: Bearer ${CLASH_SECRET}" \ -
medium Exfiltration
net-credential-useclash-switch-v2.sh:197Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer ${CLASH_SECRET}" "${CLASH_API}/proxies" | \ -
medium Exfiltration
net-credential-useclash-switch.sh:52Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer ${CLASH_SECRET}" "${CLASH_API}${endpoint}" -
medium Exfiltration
net-credential-useclash-switch.sh:58Credential used in a network call (verify the destination is the intended service)curl -s -X PUT -H "Authorization: Bearer ${CLASH_SECRET}" \
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
frontmatterSKILL.md: no YAML frontmatter block found - error
name-missingSKILL.md: frontmatter has no `name` - error
description-missingSKILL.md: no `description` — the skill can never trigger
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0When it triggers. No condition that starts the skill
- 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
- 100Tools and files. No external tools needed
- 100Steps. 27 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 416 tokens
- 100Running it twice. No mutating operations
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)
- +3Description length 0: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +4Structure: 14 headings
- +3Step-by-step instructions: 27 items
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 0.