SKILLEMALL.ai

AC willow-external-guard

Use when Willow is about to ingest, summarize, or act on external content — web fetches, jeles inbound messages, corpus archaeology files, or sub-agent outputs. Wraps untrusted content in sandwich defense markers and scans for prompt injection, role hijack, leak attacks, and approval-bypass attempts before any KB write or LLM pass.

ClawHub Agent Skills author: Sean Campbell v1.0.0 MIT-0 3 files body ≈ 1 527 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

GeneratorAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
94/100
safety, quality, tests
Safety 60%
98
Quality 40%
87
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
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 · 2

    ✓ No critical or high findings

    Medium and low: 2

    ✓ Guard found no suspicious behaviour. 2 matches are attack strings quoted in this security skill's own documentation.

    Files scanned: 3. 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 51/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 2 mutating operations with no state check
    • 60Tools and files. Uses tools (web) that frontmatter does not declare
    • 60Failures and branches. 2 branches
    • 100Steps. 15 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1527 tokens
    • 100Progress reporting. Reports progress
    • low The response is described with custom markup (4 tags): a typed call is more reliable

    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 333: enough signal without eating the budget
    • +4Structure: 14 headings
    • +3Step-by-step instructions: 15 items
    • +4Has examples (3 code blocks)
    • +3All 1 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.

    External checks

    ClawHub: clean
    This skill is a focused prompt-injection guard with a small local Python scanner and no evidence of hidden network, credential, or destructive behavior.
    LLM: benign (high) · VirusTotal: · 29 May 2026