CC test0413-6348
Security audit + append-only logging + monitoring for OpenClaw skills (file-level diff, baseline approval, SHA-256 integrity).
As a process C 62/100 · 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 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 · 15
✓ No critical or high findings
Medium and low: 15
-
medium Dangerous commands
cmd-persistenceconfig/risk-rules.json:326Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)"Register-ScheduledTask",
code literal -
medium Dangerous commands
cmd-pipe-to-shellconfig/risk-rules.json:486Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)"curl | sh",
code literal -
medium Dangerous commands
cmd-pipe-to-shellconfig/risk-rules.json:487Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)"curl | bash",
code literal -
medium Dangerous commands
cmd-pipe-to-shellconfig/risk-rules.json:488Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)"wget | sh",
code literal -
medium Dangerous commands
cmd-pipe-to-shellconfig/risk-rules.json:489Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)"wget | bash",
code literal -
medium Dangerous commands
cmd-encoded-execconfig/semantic-patterns.json:31Executes a base64/encoded payload (detector / deny-list definition; string literal in code, not executed)"needles": ["base64 -d", "| bash", "| sh"]
detectorcode literal -
low Dangerous commands
cmd-background-processconfig/risk-rules.json:315Starts a background / autostarted process (string literal in code, not executed)"systemctl enable",
code literal -
low Dangerous commands
cmd-privilegeconfig/risk-rules.json:414Privilege escalation / world-writable permissions (string literal in code, not executed)"chmod 777",
code literal -
low Dangerous commands
cmd-privilegeconfig/risk-rules.json:415Privilege escalation / world-writable permissions (string literal in code, not executed)"chmod -R 777",
code literal -
low Dangerous commands
cmd-privilegeconfig/risk-rules.json:429Privilege escalation / world-writable permissions (string literal in code, not executed)"setuid",
code literal -
low Dangerous commands
cmd-pipe-to-shellconfig/semantic-patterns.json:26Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed)"needles": ["curl | sh", "curl|sh", "wget | bash", "wget|bash"]
detectorcode literal -
low Dangerous commands
cmd-pipe-to-shellconfig/semantic-patterns.json:80Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed)"shell_markers": ["curl | sh", "curl|sh", "wget | bash", "wget|bash", "base64 -d"],
detectorcode literal
A further 3 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 12. 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 62/100
- 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, web, git, python) that frontmatter does not declare
- 65Failures and branches. 3 branches
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 70 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2356 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
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 126: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 70 items
- +4Has examples (10 code blocks)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.