BD clawned
Security agent that inventories installed OpenClaw skills, analyzes them for threats, and syncs results to your Clawned dashboard.
Security agent that inventories installed OpenClaw skills, analyzes them for threats, and syncs results to your Clawned dashboard.
As a process D 48/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.
An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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
- 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 · 13
✓ No critical or high findings
Medium and low: 13
-
medium Instruction override
en-fake-system-promptreferences/detection-patterns.md:141Fake system prompt injected into content (documentation of a security skill)### INJECT-001: System prompt override
security skill -
low Risky intent
intent-offensive-securityreferences/detection-patterns.md:46Offensive-security / dual-use content (legitimate for authorised testing; review intended use)## Reverse Shell Patterns (RSHELL-*)
-
low Risky intent
intent-offensive-securityreferences/detection-patterns.md:54Offensive-security / dual-use content (legitimate for authorised testing; review intended use)### RSHELL-002: Netcat reverse shell
-
low Risky intent
intent-offensive-securityreferences/detection-patterns.md:60Offensive-security / dual-use content (legitimate for authorised testing; review intended use)### RSHELL-003: Python reverse shell
-
low Risky intent
intent-offensive-securityreferences/detection-patterns.md:73Offensive-security / dual-use content (legitimate for authorised testing; review intended use)## Credential Harvesting Patterns (CRED-*)
-
low Risky intent
intent-offensive-securityreferences/detection-patterns.md:192Offensive-security / dual-use content (legitimate for authorised testing; review intended use)## Privilege Escalation Patterns (PRIVESC-*)
-
low Risky intent
intent-offensive-securityreferences/threat-model.md:36Offensive-security / dual-use content (legitimate for authorised testing; review intended use)### T3: Credential Harvesting (CRITICAL)
-
low Risky intent
intent-offensive-securityreferences/threat-model.md:77Offensive-security / dual-use content (legitimate for authorised testing; review intended use)### T7: Privilege Escalation (HIGH)
-
low Dangerous commands
cmd-background-processscripts/agent.py:331Starts a background / autostarted processos.setsid()
A further 4 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 4. 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 48/100
- 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
- 30Running it twice. 1 mutating operations with no state check
- 85Steps. 8 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 455 tokens
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
- -42 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 130: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (6 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.