AD skills-firewall
Security firewall for skills that automatically blocks and filters malicious or potentially harmful skills. Use when: (1) Scanning skills for security threats. (2) Checking if a skill is safe to use. (3) Filtering multiple skills based on security rules. (4) Generating security reports for skills. (5) Managing allowed/blocked skill lists. (6) Reviewing skills before installation or execution.
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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 · 9
✓ No critical or high findings
Medium and low: 9
-
low Risky intent
intent-offensive-securityreferences/malicious_patterns.md:110Offensive-security / dual-use content (legitimate for authorised testing; review intended use)## Privilege Escalation Patterns
-
low Risky intent
intent-offensive-securityreferences/malicious_patterns.md:114Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)os.system('sudo ...') # HIGH: Privilege escalationdetector -
low Risky intent
intent-offensive-securityreferences/malicious_patterns.md:115Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)subprocess.run(['sudo', ...]) # HIGH: Privilege escalation
detector -
low Dangerous commands
cmd-privilegereferences/malicious_patterns.md:121Privilege escalation / world-writable permissions (documentation of a security skill)chmod 777 file # MEDIUM: Insecure permissions
security skill -
low Risky intent
intent-offensive-securityreferences/security_rules.md:121Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Rationale**: Privilege escalation is a security risk.
-
low Dangerous commands
cmd-privilegescripts/firewall_check.py:113Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)patterns=["sudo ", "su ", "chmod 777", "chown "],
detectorcode literal -
low Dangerous commands
cmd-privilegeSKILL.md:111Privilege escalation / world-writable permissions (documentation of a security skill)| Privilege Escalation | sudo, chmod 777 | HIGH |
security skill -
low Risky intent
intent-offensive-securitySKILL.md:111Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Privilege Escalation | sudo, chmod 777 | HIGH |
A further 1 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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 46/100
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 17 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1107 tokens
- 100Running it twice. No mutating operations
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 395: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 17 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.