BF 安全卫士
安全卫士 v2.1 - 智能威胁检测、权限控制、隐私保护。L1-L4四级安全等级，13种攻击模式自动识别，中央库单点修改全局生效
As a process F 34/100 · Will not run — weak spots: steps, result and completion, when it triggers
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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 6
✓ No critical or high findings
Medium and low: 6
-
medium Dangerous commands
cmd-destructive-fsconfig/attack_cases.json:96Destructive filesystem command (wipes root/home/drive) (string literal in code, not executed; documentation of a security skill)"example": "rm -rf /; delete C:\\; chmod 777",
code literalsecurity skill -
low Dangerous commands
cmd-privilegeconfig/attack_cases.json:96Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)"example": "rm -rf /; delete C:\\; chmod 777",
code literalsecurity skill -
low Dangerous commands
cmd-privilegeconfig/central/patterns.json:97Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)"rm -rf", "delete C:", "chmod 777", "format",
detectorcode literal -
low Dangerous commands
cmd-privilegeconfig/threat_patterns.json:67Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)"sudo rm", "sudo su", "chmod 777"
code literalsecurity skill
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 24. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "permissions"
Process rating: all ten parameters 34/100
- 0Steps. Prose only: no discrete steps
- 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
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (安全卫士) differs from the folder (anquan-weishi)
- 100Tools and files. No external tools needed
- 100Execution cost. Instruction body is 577 tokens
- 100Running it twice. No mutating operations
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 64: 120–800 characters recommended
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- -212 emoji in the instructions: noise for the model
- -33 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 9 headings
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 55.