DC memos-local
Persistent local memory for OpenClaw agents. Use when users say: - "install memos" - "install MemOS" - "setup memory" - "add memory plugin" - "openclaw memory" - "memos onboarding" - "memory not working" - "configure memory" - "enable memory" - "upgrade MemOS" - "update memory plugin"
As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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.
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
- 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.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
-
high Dangerous commands
cmd-pipe-to-shellREADME_zh.md:133Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL https://cdn.memtensor.com.cn/memos-local-openclaw/install.sh | bash
-
high Dangerous commands
cmd-pipe-to-shellREADME.md:133Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL https://cdn.memtensor.com.cn/memos-local-openclaw/install.sh | bash
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:500Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL https://cdn.memtensor.com.cn/memos-local-openclaw/install.sh | bash
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:1182Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL https://cdn.memtensor.com.cn/memos-local-openclaw/install.sh | bash
Medium and low: 3
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:124Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)- Downloading and running install scripts from the internet (`curl ... | bash`, `irm ... | iex`) as a fallback
quoted -
low Obfuscation
obf-hex-escape-chainSKILL.md:697Escaped/char-code string obfuscation (quoted — discussed, not commanded)node -e "const{spawn}=require('child_process');const child=spawn(process.execPath,['-e','setTimeout(()=>{try{require(String.fromCharCode(99,104,105,108,100,95,112,114,111,99,101,115,115)).execSync(Strquoted -
low Dangerous commands
cmd-background-processSKILL.md:706Starts a background / autostarted processnohup sh -c 'sleep 10 && openclaw gateway restart' >/dev/null 2>&1 &
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 13545 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "keywords"
Process rating: all ten parameters 60/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 18 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (memos-local) differs from the folder (memos-oneclick-install)
- 40Execution cost. Instruction body is 13545 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 85Steps. 111 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 25 branches, has a failure section
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +5Description quotes 11 example trigger phrases
- +3Description length 286: enough signal without eating the budget
- +4Structure: 34 headings
- +3Step-by-step instructions: 111 items
- +4Has examples (40 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.