BC safeclaw-proxy
Install and verify the SafeClaw safety proxy for OpenClaw and other OpenAI-compatible clients. Use when setting up a local or hosted SafeClaw proxy, routing model traffic through it, debugging why calls are not appearing in the dashboard, or adapting setup for OpenClaw provider configs, agent models.json, or shell-launched clients.
As a process C 64/100 · Has gaps — weak spots: result and completion, when it triggers
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.
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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Exfiltration
net-credential-useSKILL.md:251Credential used in a network call (verify the destination is the intended service)- **401/403**: auth problem for the test curl, not necessarily a broken proxy. If `$OPENAI_API_KEY` is not set, tell the user this is expected and the proxy itself is fine
-
low Dangerous commands
cmd-pipe-to-shell-known-hostSKILL.md:150Pipe-to-shell installer from a well-known host (still executes remote code) (quoted — discussed, not commanded)2. Install uv: `curl -LsSf https://astral.sh/uv/install.sh | sh`
quoted
Files scanned: 2. 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 64/100
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, read, web, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 72 steps, 1 vague phrases
- 100Failures and branches. 25 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2889 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 333: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 72 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.