CC claw-wallet
A multi-chain wallet skill for AI agents, with local sandbox signing, secure PIN handling, and configurable risk controls.
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
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
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 12
-
high Dangerous commands
cmd-pipe-to-shellclaw-wallet.sh:27Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL "${CLAW_WALLET_BASE_URL}/install.sh" | bash
Medium and low: 11
-
medium Dangerous commands
cmd-pipe-to-shellinstall.sh:3Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)# Served at: https://www.clawwallet.cc/skills/install.sh (curl -fsSL ... | bash)
comment -
low Dangerous commands
cmd-background-processclaw-wallet.sh:78Starts a background / autostarted processif command -v setsid >/dev/null 2>&1; then
-
low Dangerous commands
cmd-background-processclaw-wallet.sh:79Starts a background / autostarted processnohup setsid "$BIN" serve >> "$LOG_FILE" 2>&1 < /dev/null &
-
low Dangerous commands
cmd-background-processclaw-wallet.sh:81Starts a background / autostarted processnohup "$BIN" serve >> "$LOG_FILE" 2>&1 < /dev/null &
-
low Dangerous commands
cmd-pipe-to-shellREADME.md:29Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill; the skill's own vendor host)curl -fsSL https://www.clawwallet.cc/install | bash
security skillvendor-host -
low Dangerous commands
cmd-pipe-to-shellSKILL.md:84Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill; the skill's own vendor host)curl -fsSL https://www.clawwallet.cc/skills/install.sh | bash
security skillvendor-host -
low Dangerous commands
cmd-pipe-to-shellskill.yml:109Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; the skill's own vendor host)- "cd skills/claw-wallet && curl -fsSL https://www.clawwallet.cc/skills/install.sh | bash"
code literalvendor-host -
low Dangerous commands
cmd-pipe-to-shellskill.yml:135Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; the skill's own vendor host)- "cd skills/claw-wallet && curl -fsSL https://www.clawwallet.cc/skills/install.sh | bash"
code literalvendor-host
A further 3 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 6. 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 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (claw-wallet) differs from the folder (wallet-test)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4014 tokens
- 100Steps. 94 steps
- 100Failures and branches. 6 branches, has a failure section
- 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 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (18 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
- +1No license
- +2Single-language instructions
- +3Description length 122: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 94 items
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.