CC safe-skill-advisor
Security Skill Advisor - Protect you from malicious skills on ClawHub. Provides security warnings, tool recommendations, and 30-second self-check checklist.
As a process C 52/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 14
✓ No critical or high findings
Medium and low: 14
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:226Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)| curl \| bash | 30% | Directly execute remote malicious scripts |
security skill -
medium Dangerous commands
cmd-pipe-to-shell测试报告.md:66Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)- SKILL.md 里有没有要求执行 curl | bash 或下载外部文件？
security skill -
medium Dangerous commands
cmd-pipe-to-shell测试报告.md:118Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)- ❌ 要求执行 curl http://... | bash
security skill -
medium Dangerous commands
cmd-pipe-to-shell测试报告.md:364Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)A. 技能要求执行 curl http://... | bash
security skill -
low Risky intent
intent-wallet-secretsREADME.md:92Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)- "Wallet Private Key Manager"
quoted -
low Risky intent
intent-wallet-secretsSKILL.md:63Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)- 🪙 Cryptocurrency tools ("Free BTC Mining", "Wallet Private Key Manager")quoted -
low Risky intent
intent-offensive-securitySKILL.md:225Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Password-Protected ZIP | 45% | Bypass antivirus detection |
-
low Risky intent
intent-wallet-secretsSKILL.md:382Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)1. 🪙 Cryptocurrency: "Free BTC Mining", "Wallet Private Key Manager"
quoted
A further 6 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "homepage"
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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 100Steps. 115 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2846 tokens
- 100Running it twice. Mutating operations check current state
- low 14 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
- -267 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 156: enough signal without eating the budget
- +4Structure: 32 headings
- +3Step-by-step instructions: 115 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.