DD 🦒 Giraffe Guard — 长颈鹿卫士
Scan OpenClaw skill directories for supply chain attacks and malicious code. 扫描 OpenClaw skill 目录，检测潜在的供应链投毒和恶意代码。
Scan OpenClaw skill directories for supply chain attacks and malicious code.
As a process D 41/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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.
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
- 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.
- 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 · 11
-
high Dangerous commands
cmd-encoded-execscripts/ast_analyzer.py:263Executes a base64/encoded payload (string literal in code, not executed)"base…ode() result passed to exec/eval",
code literal -
high Dangerous commands
cmd-encoded-execscripts/ast_analyzer.py:371Executes a base64/encoded payload (code comment)# Parent annotator (needed for b64decode→exec chain detection)
comment
Medium and low: 9
-
medium Dangerous commands
cmd-encoded-execscripts/ast_analyzer.py:252Executes a base64/encoded payload (detector / deny-list definition; code comment)# ── Rule: base…ode chained with exec ───────────
detectorcomment -
medium Exfiltration
exfil-read-secret-filesscripts/audit.sh:884Reads credential / secret files (documentation of a security skill)find "$dir" -type f \( -name "credentials.json" -o -name "service-account*.json" -o -name ".pypirc" \) ! -path "*/.git/*" 2>/dev/null | while read -r f; do
security skill -
medium Exfiltration
exfil-read-secret-filesscripts/audit.sh:888Reads credential / secret files (documentation of a security skill)find "$dir" -type f -name ".npmrc" ! -path "*/.git/*" 2>/dev/null | while read -r f; do
security skill -
low Risky intent
intent-offensive-securitySKILL.md:69Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| 5 | reverse-shell | Reverse shell patterns | 反向 shell |
-
low Risky intent
intent-offensive-securitySKILL.md:101Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| 20 | skillmd-privilege-escalation | Privilege escalation | 权限提升 |
A further 4 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 41/100
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (🦒 Giraffe Guard — 长颈鹿卫士) differs from the folder (giraffe-guard)
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 100Steps. 10 steps
- 100Execution cost. Instruction body is 1032 tokens
- 100Running it twice. No mutating operations
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)
- +3Description length 114: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -31 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 14 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.