SKILLEMALL.ai

BF agent-security-guard

Runtime interaction guard for Hermes/OpenClaw: a deterministic transition policy engine that keeps reading, browsing, and summarizing free while stripping command-authority from untrusted content. Separates origin trust from data sensitivity, classifies actions into tiers, blocks dangerous kill-chains (read secret -> external post, web -> shell, download -> execute, untrusted -> privileged memory), wraps untrusted content as data (not instructions), and emits machine-readable decisions with audit. Default mode: autonomous-safe.

ClawHub Hermes author: xMannixx v0.1.0 MIT-0 2 files body ≈ 521 tokens Open the sourceclawhub.ai analyzed 20 h ago

Runtime interaction guard for Hermes/OpenClaw: a deterministic transition policy engine that keeps reading, browsing, and summarizing free while stripping…

As a process F 22/100 · Will not run — References files that are not bundled: references/self-modification.md

AnalyzerAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
82/100
safety, quality, tests
Safety 60%
100
Quality 40%
54
Run on models
none yet
Process rating
F
22/100
Will not run
References files that are not bundled: references/self-modification.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
  3. The text references files that are not there: add them or drop the references.
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 · 0

✓ No critical or high findings

Files scanned: 0. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 533 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning description-no-when neither description nor a "## When to Use" section says when to use the skill
  • warning missing-ref reference to a missing file: references/self-modification.md

Process rating: all ten parameters 22/100

Will not run. References files that are not bundled: references/self-modification.md
  • 0Tools and files. 1 referenced file(s) missing: references/self-modification.md
  • 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
  • 30Running it twice. 1 mutating operations with no state check
  • 50Steps. 2 steps
  • 60Consistency. The Hermes dialect needs category and tags
  • 100Execution cost. Instruction body is 521 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

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3No numbered steps or checklist
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +2Single-language instructions
  • +3Description length 533: enough signal without eating the budget
  • +4Structure: 4 headings
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 54.

External checks

ClawHub: clean
The artifacts describe coherent ClawHub/Convex workflow skills with disclosed admin and migration powers, guarded by user confirmation and existing authenticated tools.
LLM: benign (high) · VirusTotal: · 28 Jun 2026