BC active-defense-sentinal
Defensive triage skill for OpenClaw, Hermes Agent, host integrity, and OpenClaw skill-supply-chain scanning. Detects prompt injection, session drift, context overflow, host anomalies, and unsafe skills while keeping actions bounded and auditable.
As a process C 62/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, running it twice
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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
-
low Concealment
en-hide-from-userreferences/skill-scanner-adapter.md:47Instruction to hide actions from the user (negated — the text forbids it)- Never silently install a skill that has not been scanned
negated -
low Concealment
en-hide-from-userSKILL.md:162Instruction to hide actions from the user (negated — the text forbids it)- Do not silently install an unscanned skill
negated
Files scanned: 32. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 62/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 93 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1398 tokens
- low 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (8 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)
- +4No input/output examples
- -49 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 246: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 93 items
- +3Output format is stated explicitly
- +3All 8 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.
External checks
ClawHub: suspicious
This appears to be a defensive security skill, but it exposes sensitive host and browser-session details and can modify installed skills, so users should review it before installing.
LLM: suspicious (high) · VirusTotal: · 29 May 2026