DD safe-exec
Safe command execution for OpenClaw Agents with automatic danger pattern detection, risk assessment, user approval workflow, and audit logging. Use when agents need to execute shell commands that may be dangerous (rm -rf, dd, fork bombs, system directory modifications) or require human oversight. Provides multi-level risk assessment (CRITICAL/HIGH/MEDIUM/LOW), in-session notifications, pending request management, and non-interactive environment support for agent automation.
As a process D 45/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
The same skill appears in 2 more places: ClawHub, ClawHub
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.
- 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 · 24
-
high Dangerous commands
cmd-destructive-fsREADME_EN.md:189Destructive filesystem command (wipes root/home/drive) (documentation of a security skill)• rm -rf / (delete system files)
security skill
Medium and low: 23
-
medium Dangerous commands
cmd-pipe-to-shellREADME_EN.md:192Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)• curl | bash (code injection)
security skill -
medium Dangerous commands
cmd-destructive-fsscripts/safe-exec.sh:187Destructive filesystem command (wipes root/home/drive) (detector / deny-list definition; string literal in code, not executed)if [[ "$cmd" == *":(){:|:&};:"* ]] || [[ "$cmd" == *":(){ :|:& };:"* ]]; thendetectorcode literal -
low Risky intent
intent-offensive-securityREADME_EN.md:35Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)| 🟠 **HIGH** | `chmod 777` | Privilege escalation |
detector -
low Dangerous commands
cmd-privilegeREADME_EN.md:191Privilege escalation / world-writable permissions (documentation of a security skill)• chmod 777 (privilege escalation)
security skill -
low Risky intent
intent-offensive-securityREADME_EN.md:191Offensive-security / dual-use content (legitimate for authorised testing; review intended use)• chmod 777 (privilege escalation)
-
low Dangerous commands
cmd-privilegeREADME_EN.md:531Privilege escalation / world-writable permissions (documentation of a security skill)- Privilege escalation (chmod 777, sudo)
security skill -
low Risky intent
intent-offensive-securityREADME_EN.md:531Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Privilege escalation (chmod 777, sudo)
A further 16 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 45/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, git) that frontmatter does not declare
- 100Steps. 57 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1955 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 17 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)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- -220 emoji in the instructions: noise for the model
- -34 of 5 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 478: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 57 items
- +4Has examples (16 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.