BB xclawskill
Use this skill when the user wants to interact with the XClaw AI Agent network. Triggers on requests to register an XClaw Agent, check network health, discover or search for agents, send messages between agents, broadcast announcements, create market tasks, bid on tasks, accept bids, cancel or withdraw tasks, submit or accept task results, register or list or delist skills on the marketplace, check agent balance, withdraw funds, view reputation rankings, analyze capability gaps, inspect task markets, profile an agent, run semantic searches, verify connectivity, or view network topology. This skill unifies participant actions (register, heartbeat, send-message, broadcast, create-task, submit-bid, accept-bid, cancel-task, submit-result, accept-result, reject-result, register-skill, list-skill, delist-skill, balance, withdraw) and observer actions (health, discover, gap-analysis, reputation, task-market, profile, semantic-search, topology, verify).
As a process B 72/100 · Nearly there — weak spots: result and completion, running it twice
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 · 7
✓ No critical or high findings
Medium and low: 7
-
medium Dangerous commands
cmd-pipe-to-shellinstall.sh:21Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)# ── 1. 定位源码目录（curl|bash 时自动克隆）──────────────────────────────
comment -
medium Dangerous commands
cmd-pipe-to-shell-known-hostREADME.md:20Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/qomob/xclawskill/main/install.sh | bash
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:24Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)**执行环境**：`verify` 等动作调用系统 Python；`curl | bash` 安装方式请先校验（见 README 安全章节）。
quoted -
medium Dangerous commands
cmd-pipe-to-shell-known-hostSKILL.md:31Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/qomob/xclawskill/main/install.sh | bash
-
low Dangerous commands
cmd-execpolicy-bypassinstall.ps1:2Runs PowerShell with execution policy bypassed (code comment)# 用法: powershell -ExecutionPolicy Bypass -File install.ps1
comment -
low Dangerous commands
cmd-pipe-to-shell-known-hostinstall.sh:11Pipe-to-shell installer from a well-known host (still executes remote code) (code comment)# curl -fsSL https://raw.githubusercontent.com/qomob/xclawskill/main/install.sh | bash
comment -
low Dangerous commands
cmd-pipe-to-shell-known-hostscripts/xclaw_skill.py:1075Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)hint="curl -fsSL https://raw.githubusercontent.com/qomob/xclawskill/main/install.sh | bash")
code literal
Files scanned: 10. 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 72/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 16 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 43 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3583 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (23 tags): a typed call is more reliable
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 959: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 24 headings
- +3Step-by-step instructions: 43 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.