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.
As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, consistency, running it twice
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 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
- 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-securityreferences/quick-test.md:63Offensive-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.