DC clickstack-otel-collector
Use when a user wants to wire an OpenTelemetry collector into a Managed ClickStack service on ClickHouse Cloud, either by deploying a new local collector (Docker run or Docker Compose) or by configuring their own existing collector, then send rich synthetic telemetry and verify it is visible in ClickStack.
Use when a user wants to wire an OpenTelemetry collector into a Managed ClickStack service on ClickHouse Cloud, either by deploying a new local collector…
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:100Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)- The `clickhousectl` install in Step 3 uses `curl … | sh`, which many agent sandboxes flag as
quoted -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:191Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)installer: the `|| curl … | sh` form drags a harmless check into a compound command that sandboxes
quoted -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:201Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)curl -fsSL https://clickhouse.com/cli | sh
vendor-host -
medium Exfiltration
net-credential-useSKILL.md:741Credential used in a network call (verify the destination is the intended service)2. Confirm the `authorization` header matches `$OTLP_AUTH_TOKEN`: `grep -c Unauthenticated
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 9744 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 842): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 59/100
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 36 mutating operations with no state check
- 40Execution cost. Instruction body is 9744 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 34 steps
- 100Failures and branches. 8 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
- 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
- +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
- -2localhost URLs: will not work for another user
- +2Single-language instructions
- +3Description length 307: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (33 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.