BD Shell Script Helper
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━. Use when you need shell script capabilities. Triggers on: shell script.
As a process D 45/100 · Unfinished process — 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-destructive-fsscripts/shell.sh:383Destructive filesystem command (wipes root/home/drive) (detector / deny-list definition; string literal in code, not executed)grep -nE 'rm -rf /' "$file" && echo "🚨 危险: 检测到 rm -rf / ！" && ((issues++))
detectorcode literal -
low Exfiltration
exfil-webhook-urlscripts/shell.sh:94Webhook / callback URL commonly used for exfiltration (verify the destination) (code comment; quoted — discussed, not commanded)# curl -s -X POST "https://hooks.slack.com/services/YOUR/WEBHOOK" \\
commentquoted -
low Exfiltration
exfil-webhook-urlscripts/shell.sh:239Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)# ALERT_WEBHOOK="https://hooks.slack.com/services/..."
placeholder
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: All mapping items must start at the same column at line 4, column 1: description: "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━. Use when you need… Shell脚本助手。脚本生成、逐行解释、调试排错、常用模板(备份/监控/部署)、一行命令、Bash速查表。Shell script generator, … ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "source"
Process rating: all ten parameters 45/100
- 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
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (Shell Script Helper) differs from the folder (shell-script)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 9 steps
- 100Execution cost. Instruction body is 216 tokens
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 119: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -32 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 6 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.