FD openclaw-gateway-manager
(no description)
Not recommendedcritical or high security findings · low grade F
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
Dangerous commands
If you install
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.
For the author
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
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Add a description to the frontmatter: without it the skill never triggers.
For the model run — optional
- 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 · 10
-
high Dangerous commands
cmd-persistencescripts/common.sh:301Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl bootstrap "gui/$(id -u)" "$service_file" >/dev/null 2>&1 || launchctl load "$service_file" >/dev/null 2>&1
-
high Dangerous commands
cmd-persistenceSKILL.md:413Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load ~/Library/LaunchAgents/ai.openclaw.gateway.plist
-
high Dangerous commands
cmd-persistenceSKILL.md:499Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load ~/Library/LaunchAgents/ai.openclaw.gateway.plist
Medium and low: 7
-
medium Dangerous commands
cmd-persistenceREADME.en.md:208Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)- Creates user-level services only (`~/Library/LaunchAgents/` or `~/.config/systemd/user/`)
quoted -
medium Dangerous commands
cmd-persistencescripts/common.sh:51Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)launchagent) echo "$HOME/Library/LaunchAgents/$service_name.plist" ;;
code literal -
medium Dangerous commands
cmd-persistenceSKILL.md:201Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)- 仅创建用户级服务（`~/Library/LaunchAgents/` 或 `~/.config/systemd/user/`）
quoted -
medium Dangerous commands
cmd-persistenceSKILL.md:379Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)- Creates user-level services only (`~/Library/LaunchAgents/` or `~/.config/systemd/user/`)
quoted -
medium Dangerous commands
cmd-persistenceSKILL.md:456Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)- ✅ 仅用户级服务（`~/Library/LaunchAgents/` 或 `~/.config/systemd/user/`）
quoted
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
frontmatterSKILL.md: no YAML frontmatter block found - error
name-missingSKILL.md: frontmatter has no `name` - error
description-missingSKILL.md: no `description` — the skill can never trigger
Process rating: all ten parameters 46/100
- 0Result and completion. Does not say what the result is
- 0When it triggers. No condition that starts the skill
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 18 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 87 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3341 tokens
- low 24 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)
- +3Description length 0: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- -2111 emoji in the instructions: noise for the model
- -41 reference files, but SKILL.md never points to them: the model will not open them
- -31 of 9 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 54 headings
- +3Step-by-step instructions: 87 items
- +4Has examples (12 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 0.
External checks
ClawHub: suspicious
This looks like a real OpenClaw gateway manager, but it needs review because it can create auto-start background services and delete local instance directories while using loosely validated user inputs.
LLM: suspicious (high) · VirusTotal: · 29 May 2026