SKILLEMALL.ai

BC memory-shield

Protect agent memory: snapshot before compaction, scan memory/snapshot files for prompt-injection, secrets, and contradictions, audit what changed. Use when hardening agent memory or auditing for indirect prompt injection. Don't use for general code SAST or SQL scanning.

ClawHub Hermes author: ViBo v0.1.5 MIT-0 8 files body ≈ 1 149 tokens Open the sourceclawhub.ai analyzed 3 d ago

Protect agent memory: snapshot before compaction, scan memory/snapshot files for prompt-injection, secrets, and contradictions, audit what changed.

As a process C 53/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

AnalyzerAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
87/100
safety, quality, tests
Safety 60%
88
Quality 40%
85
Run on models
none yet
Process rating
C
53/100
Has gaps
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

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Instruction override medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.

For the author

An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
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 · 4

✓ No critical or high findings

Medium and low: 4
  • medium Instruction override en-ignore-previous README.md:60
    Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)
    memo…:14 [injected] looks injected: IGNORE ALL PREVIOUS INSTRUCTIONS...
    security skill
  • medium Instruction override en-ignore-previous SKILL.md:113
    Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)
    memo…:14 [injected] looks injected: IGNORE ALL PREVIOUS INSTRUCTIONS...
    security skill

A further 2 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 271 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • note frontmatter-key unknown frontmatter key "tools"

Process rating: all ten parameters 53/100

  • 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
  • 30Running it twice. 4 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 60Consistency. The Hermes dialect needs category and tags
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 28 steps
  • 100Execution cost. Instruction body is 1149 tokens
  • 100Progress reporting. Reports progress
  • 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
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 271: enough signal without eating the budget
  • +4Structure: 10 headings
  • +3Step-by-step instructions: 28 items
  • +4Has examples (4 code blocks)
  • +3All 4 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.

External checks

ClawHub: clean
This skill reads user-selected memory files to create snapshots and scan reports, with no evidence of hidden network access, deletion, or persistence.
LLM: benign (high) · VirusTotal: · 28 Aug 2026