SKILLEMALL.ai

BC agent-hardening

Lock down any LLM agent against prompt injection, data exfiltration, social engineering, and channel-based attacks. Use when setting up a new agent, auditing an existing agent's security posture, hardening an agent that handles sensitive data, reviewing MCP server permissions, or when someone says "how do I make this agent more secure" or "protect against prompt injection." Works with OpenClaw, Claude Code, LangChain, custom MCP setups, and any agent framework that accepts natural-language input and calls external tools.

ClawHub Agent Skills author: Don Zurbrick v1.1.0 MIT-0 9 files body ≈ 870 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, consistency, running it twice

AnalyzerAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
89/100
safety, quality, tests
Safety 60%
87
Quality 40%
92
Run on models
none yet
Process rating
C
63/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

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".

For the author

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

    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 · 9

    ✓ No critical or high findings

    Medium and low: 9
    • low Risky intent intent-offensive-security references/quick-test.md:63
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (test fixture / example file)
      ### MT-1. Gradual privilege escalation
      fixture

    A further 8 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 9. 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 63/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 2 mutating operations with no state check
    • 40Consistency. Frontmatter name (agent-hardening) differs from the folder (agent-hardening-zurbrick)
    • 50When it triggers. No condition that starts the skill
    • 55Failures and branches. 1 branches
    • 60Result and completion. Output format stated, no completion criterion
    • 100Tools and files. No external tools needed
    • 100Steps. 33 steps
    • 100Execution cost. Instruction body is 870 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

    • +4Description does not say when NOT to use the skill (false activations)
    • +4No input/output examples
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 2 example trigger phrases
    • +3Description length 526: enough signal without eating the budget
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 33 items
    • +3Output format is stated explicitly
    • +4Reference files are cited in the instructions (6 of 6)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.

    External checks

    ClawHub: clean
    This is a coherent agent-security guide with an optional test runner, but users should be careful with its email-copying advice and system-prompt testing script.
    LLM: benign (medium) · VirusTotal: · 29 May 2026