BD skillfence
Runtime security monitor for OpenClaw skills. Watches what your installed skills actually DO — network calls, file access, credential reads, process activity. Not a scanner. A watchdog.
Runtime security monitor for OpenClaw skills.
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 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.
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
- 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 · 7
✓ No critical or high findings
Medium and low: 7
-
medium Exfiltration
intent-browser-credential-storemonitor.js:124Accesses a browser credential / cookie store (quoted — discussed, not commanded)"cookies.sqlite",
quoted -
medium Exfiltration
intent-browser-credential-storemonitor.js:125Accesses a browser credential / cookie store (quoted — discussed, not commanded)"Login Data", // Chrome passwords
quoted -
medium Exfiltration
intent-browser-credential-storemonitor.js:127Accesses a browser credential / cookie store (quoted — discussed, not commanded)"Local State", // Chrome encryption key
quoted -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:155Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)| curl\|sh pipe attacks | Pattern matching | HIGH |
security skill -
low Risky intent
intent-offensive-securitySKILL.md:21Offensive-security / dual-use content (legitimate for authorised testing; review intended use)backdoor that hid a reverse shell inside a working market search function.
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
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
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 36 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1886 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (5 tags): a typed call is more reliable
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
- -214 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 185: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 36 items
- +4Has examples (11 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.