SKILLEMALL.ai

AC Input Safety Guard

Lightweight two-stage input safety guard for agents. Use this skill when an agent must screen user input before answering, block prompt injection or prompt leakage attempts, classify risky requests, and either return a safe answer or an interception response. The workflow is stage1 deterministic prefilter plus stage2 agent-native semantic review.

ClawHub Agent Skills author: SkywingsWang v1.0.0 MIT-0 8 files body ≈ 1 637 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, consistency

ProcedureAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
90/100
safety, quality, tests
Safety 60%
97
Quality 40%
79
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
Progress reporting w 2
0
When it triggers w 12
20
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 · 3

    ✓ No critical or high findings

    Medium and low: 3

    ✓ Guard found no suspicious behaviour. 3 matches are attack strings quoted in this security skill's own documentation.

    Files scanned: 8. 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)

    Process rating: all ten parameters 56/100

    • 0Result and completion. Does not say what the result is
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 3 mutating operations with no state check
    • 40Consistency. Frontmatter name (Input Safety Guard) differs from the folder (input-safety-guard)
    • 60Tools and files. Uses tools (python) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 88 steps
    • 100Failures and branches. 1 branches, has a failure section
    • 100Execution cost. Instruction body is 1637 tokens
    • low 10 top-level sections: this looks like several domains in one skill

    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 348: enough signal without eating the budget
    • +4Structure: 11 headings
    • +3Step-by-step instructions: 88 items
    • +4Has examples (1 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.

    External checks

    ClawHub: clean
    This is a coherent input-screening skill that checks user messages before answering and does not show hidden data access, persistence, or destructive behavior.
    LLM: benign (high) · VirusTotal: · 29 May 2026