BF volcengine-iac
Use Terraform/IaC for Volcengine resources only when the user explicitly chooses Terraform/IaC, already has a Terraform workflow/state, or confirms they need plan/diff/drift/destroy safety for VKE, managed databases/cache/storage, load balancers, domains/certificates, logging/monitoring, or team-managed infrastructure.
Use Terraform/IaC for Volcengine resources only when the user explicitly chooses Terraform/IaC, already has a Terraform workflow/state, or confirms they need…
As a process F 58/100 · Will not run — References files that are not bundled: assets/examples/, references/volcenginecc-*.md, assets/modules/
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.
The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.
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.
- The text references files that are not there: add them or drop the references.
- 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
-
high Exfiltration
exfil-read-secret-filesreferences/provider-versions.md:169Reads credential / secret files- `volcengine_vke_cluster.kubeconfig_private` and `kubeconfig_public` are base…ed. Pipe through `base64 -d` before writing to `~/.kube/config`.
Medium and low: 3
-
medium Secrets in code
secret-private-keyreferences/volcenginecc-alb.md:90Private key material (key header without key body; quoted — discussed, not commanded)4. `volcenginecc_alb_certificate` with `certificate_type = "Server"` is verified with a PEM certificate plus a traditional RSA private key (`-----BEGIN PRIVATE KEY----- …
header onlyquoted -
medium Secrets in code
secret-private-keyreferences/volcenginecc-clb.md:72Private key material (key header without key body; quoted — discussed, not commanded)6. `volcenginecc_clb_certificate` requires a PEM certificate plus a traditional RSA private key (`-----BEGIN PRIVATE KEY----- …
header onlyquoted -
low Secrets in code
secret-password-literalreferences/volcenginecc-blocked.md:602Hard-coded password / key literal (may be an example)password = var.…e64
Files scanned: 57. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: assets/examples/ - warning
missing-refreference to a missing file: references/volcenginecc-*.md - warning
missing-refreference to a missing file: assets/modules/ - warning
missing-refreference to a missing file: assets/examples/volcengine-vke-cr-nginx/ - note
edit-residuethe text marks something as outdated (lines 6, 18, 20, 62, 80, 127): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 58/100
- 0Tools and files. 4 referenced file(s) missing: assets/examples/, references/volcenginecc-*.md, assets/modules/
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 22 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 38 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3734 tokens
- low 13 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 320: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 38 items
- +4Has examples (12 code blocks)
- +4Reference files are cited in the instructions (4 of 51)
- +3All 4 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.