SKILLEMALL.ai

BD OpenClaw Bash Safety — Why Your Agent Is a Security Risk

Understand the attack surface created when an OpenClaw agent executes shell commands autonomously. Covers obfuscation, injection, encoding attacks, and why ClawHavoc compromised 341 skills. Free primer for the Bash Security Validator skill.

ClawHub Agent Skills author: ~K¹yle Million v1.0.1 MIT-0 2 files body ≈ 1 428 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process D 39/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
B
89/100
safety, quality, tests
Safety 60%
99
Quality 40%
74
Run on models
none yet
Process rating
D
39/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • 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 · 1

    ✓ No critical or high findings

    Medium and low: 1

    ✓ Guard found no suspicious behaviour. 1 matches are attack strings quoted in this security skill's own documentation.

    Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
    • note frontmatter-key unknown frontmatter key "slug"

    Process rating: all ten parameters 39/100

    • 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
    • 30Running it twice. 2 mutating operations with no state check
    • 40Consistency. Frontmatter name (OpenClaw Bash Safety — Why Your Agent Is a Security Risk) differs from the folder (free-bash-safety-primer)
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 100Steps. 4 steps
    • 100Execution cost. Instruction body is 1428 tokens

    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
    • +4No input/output examples
    • +1No license
    • +2Single-language instructions
    • +3Description length 240: enough signal without eating the budget
    • +4Structure: 6 headings
    • +3Step-by-step instructions: 4 items

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.

    External checks

    ClawHub: clean
    This is a read-only bash safety primer with no code, credentials, persistence, or privileged behavior.
    LLM: benign (high) · 28 May 2026