AB qshell-copilot
Manage files on Qiniu Cloud Storage (Kodo) via the qshell CLI tool: upload, download, list, delete, copy, move files, CDN refresh/prefetch, and bucket management. Use this skill whenever the user mentions Qiniu, qiniu, qshell, Kodo, uploading to cloud storage, CDN operations, object storage buckets, or managing remote files on Qiniu's platform. Also trigger when the user asks to transfer local files to a Chinese cloud storage provider, fetch remote URLs into a storage bucket, generate private download links, or batch-upload a directory. Even if the user simply says "upload this to my bucket" or "list my cloud files" in a context where Qiniu is the configured provider, use this skill.
As a process B 73/100 · Nearly there — weak spots: result and completion, progress reporting
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
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 2
✓ No critical or high findings
Medium and low: 2
-
medium Dangerous commands
cmd-privilegereferences/install-guide.md:38Privilege escalation / world-writable permissionssudo mv qshell /usr/local/bin/
-
medium Dangerous commands
cmd-privilegereferences/install-guide.md:48Privilege escalation / world-writable permissionssudo mv qshell /usr/local/bin/
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 73/100
- 0Result and completion. Does not say what the result is
- 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. 7 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 6 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1439 tokens
- 100Running it twice. Mutating operations check current state
- low The response is described with custom markup (27 tags): a typed call is more reliable
- medium 4 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
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
- +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
- +5Description quotes 2 example trigger phrases
- +3Description length 692: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 7 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.