BC volcengine-tosutil
Use when the user mentions tosutil, TOS object storage, bucket/object operations, batch upload or download, object metadata, TOS connectivity, or errors such as 403/network/argument failures. 围绕火山引擎对象存储 tosutil 生成与校验命令、规划桶/对象操作并诊断错误；当用户提到 tosutil、TOS 桶对象管理、批量上传下载或相关排障时调用。
Use when the user mentions tosutil, TOS object storage, bucket/object operations, batch upload or download, object metadata, TOS connectivity, or errors such…
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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.
How to improve
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
medium Dangerous commands
cmd-privilegeSKILL.md:73Privilege escalation / world-writable permissionssudo mv tosutil /usr/local/bin
-
medium Dangerous commands
cmd-privilegeSKILL.md:81Privilege escalation / world-writable permissionssudo mv tosutil /usr/local/bin
-
medium Dangerous commands
cmd-privilegeSKILL.md:89Privilege escalation / world-writable permissionssudo mv tosutil /usr/local/bin
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 18, 278): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 52/100
- 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
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 121 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2310 tokens
- 100Running it twice. No mutating operations
- low 18 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 272: enough signal without eating the budget
- +4Structure: 42 headings
- +3Step-by-step instructions: 121 items
- +4Has examples (18 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 4 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.