SKILLEMALL.ai
GitHub ↗ RU Sign in

AD eridian-carapace

Agent security hardening and prompt injection defense for OpenClaw. Protects against ClawHavoc-style attacks including prompt injection, data exfiltration, credential theft, and unauthorized operations. Runtime protection that complements pre-installation skill scanners like Clawdex. Includes security audit checklist, 8 documented attack vector defenses with mitigations, copy-paste AGENTS.md security patterns, credential file protection, browser URL allowlisting, and sensitive operation approval flows. Use when setting up agent security, performing security audits, hardening agent configurations, protecting credentials, preventing data leaks, or defending against indirect prompt injection attacks.

modbender/skill-library-mcp Agent Skills author: modbender MIT 4 files body ≈ 1 461 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Agent security hardening and prompt injection defense for OpenClaw.

As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
92/100
safety, quality, tests
Safety 60%
94
Quality 40%
88
Run on models
none yet
Process rating
D
46/100
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 · 6

    ✓ No critical or high findings

    Medium and low: 6
    • low Risky intent intent-offensive-security references/attack-vectors.md:41
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ## 3. Credential Harvesting
    • low Risky intent intent-offensive-security references/attack-vectors.md:57
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ## 4. Privilege Escalation via Config Modification
    • low Risky intent intent-offensive-security references/audit-template.md:109
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ## 4. Penetration Testing

    A further 3 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 4. 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 46/100

    • 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
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 100Steps. 64 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1461 tokens
    • 100Running it twice. Mutating operations check current state
    • 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 706: enough signal without eating the budget
    • +4Structure: 15 headings
    • +3Step-by-step instructions: 64 items
    • +4Has examples (1 code blocks)
    • +4Reference files are cited in the instructions (3 of 3)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.