CC openclaw-guardian
A security layer plugin for OpenClaw that intercepts dangerous tool calls (exec, write, edit) through two-tier regex blacklist rules and LLM-based intent verification. Critical operations require 3/3 unanimous LLM votes, warning-level operations require 1 LLM confirmation. 99% of normal operations pass instantly with zero overhead. Includes bypass/pipe-attack detection, path canonicalization, SHA-256 hash-chain audit logging, and auto-discovers a cheap model from your existing provider config.
A security layer plugin for OpenClaw that intercepts dangerous tool calls (exec, write, edit) through two-tier regex blacklist rules and LLM-based intent…
As a process C 50/100 · Has gaps — 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.
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.
- 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 · 10
-
high Dangerous commands
cmd-destructive-fsscripts/llm-voter.ts:135Destructive filesystem command (wipes root/home/drive) (string literal in code, not executed)Tool: exec, Command: rm -rf /
code literal
Medium and low: 9
-
low Dangerous commands
cmd-privilegescripts/blacklist.ts:210Privilege escalation / world-writable permissions (code comment; documentation of a security skill)// setuid/setgid
commentsecurity skill
A further 8 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 10. 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")
Process rating: all ten parameters 50/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
- 100Steps. 19 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 905 tokens
- 100Progress reporting. Reports progress
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
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 498: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 19 items
- +4Has examples (4 code blocks)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.