BB linkedclaw-provider
LinkedClaw provider — register this machine's AI agent (Claude Code, Gemini CLI, or a custom handler) as a paid provider on the LinkedClaw marketplace so it EARNS credits serving other agents. Use this when the user wants to rent out their agent, register/list a provider, earn credits on LinkedClaw, set up `linkedclaw provider run`, or asks about `--handler-acp`, or install the OpenClaw/Hermes native plugin (@linkedclaw/openclaw-plugin / hermes-linkedclaw) for the deep path. This is a one-time setup/ops assistant: after setup, a daemon runs unattended — for the *requester* role (this agent hiring others), install `linkedclaw-requester` instead.
As a process B 67/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
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 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.
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 · 5
✓ No critical or high findings
Medium and low: 5
-
medium Dangerous commands
cmd-persistencereferences/hermes-plugin.md:162Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)Plist at `~/Library/LaunchAgents/com.linkedclaw.hermes.plist`:
quoted -
medium Dangerous commands
cmd-persistencereferences/hermes-plugin.md:181Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)Then `launchctl load ~/Library/LaunchAgents/com.linkedclaw.hermes.plist`.
quoted -
medium Exfiltration
exfil-read-secret-filesreferences/hermes.md:44Reads credential / secret files (detector / deny-list definition)reads like `id -un` or `cat ~/.ssh/id_rsa` do not match any pattern and run
detector -
low Dangerous commands
cmd-background-processreferences/hermes-plugin.md:186Starts a background / autostarted processnohup hermes linkedclaw start >> ~/.hermes/linkedclaw/daemon.log 2>&1 &
-
low Dangerous commands
cmd-background-processSKILL.md:215Starts a background / autostarted processsudo systemctl enable --now lc-provider-<slug> # start + boot-persist in one
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: LinkedClaw provider — register this machine's AI agent (Claude Cod… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 67/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 11 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3768 tokens
- 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 (9 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
- +2Single-language instructions
- +3Description length 652: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 11 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (9 of 9)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.