SKILLEMALL.ai
GitHub ↗ RU Sign in

CD agent-memory-improved

Run a local Agent Memory Service for persistent self-improvement with proper Ed25519 cryptography. Fixed signature implementation for reliable memory storage and retrieval.

modbender/skill-library-mcp Agent Skills author: modbender MIT 12 files · 2 scripts body ≈ 731 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Run a local Agent Memory Service for persistent self-improvement with proper Ed25519 cryptography.

As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
C
63/100
safety, quality, tests
Safety 60%
59
Quality 40%
69
Run on models
none yet
Process rating
D
49/100
Unfinished process
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.

Risky intent 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 purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.

For the author

Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.

How to improve

  1. 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 · 21

✓ No critical or high findings

Medium and low: 21
  • medium Risky intent intent-wallet-secrets CHANGELOG.md:9
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    - Properly derives Ed25519 private key from BIP39 recovery phrase
  • medium Risky intent intent-wallet-secrets CHANGELOG.md:13
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    - Fixed private key derivation from recovery phrase
  • medium Risky intent intent-wallet-secrets README.md:55
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    Save your recovery phrase! It's the only way to recover your identity.
  • medium Risky intent intent-wallet-secrets SKILL.md:14
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    - **Correct key derivation** - Private key properly derived from BIP39 recovery phrase
  • medium Risky intent intent-wallet-secrets SKILL.md:85
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    - Recovery phrase for identity backup
  • low Risky intent intent-wallet-secrets assets/service/main.py:8
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    - Recover using a BIP39-style recovery phrase
    quoted
  • low Risky intent intent-wallet-secrets assets/service/main.py:98
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    message: str = "Save your recovery phrase! It's the only way to recover your identity."
    quoted
  • low Risky intent intent-wallet-secrets assets/service/main.py:102
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    recovery_phrase: str = Field(..., min_length=10, description="BIP39 recovery phrase")
    quoted
  • low Risky intent intent-wallet-secrets assets/service/main.py:206
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    """Generate BIP39 recovery phrase from private key"""
    quoted
  • low Risky intent intent-wallet-secrets assets/service/main.py:293
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    IMPORTANT: Save the recovery phrase! It's the only way to recover your identity.
    quoted
  • low Risky intent intent-wallet-secrets scripts/memory_client_original.py:42
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    """Recover private key from recovery phrase."""
    quoted
  • low Risky intent intent-wallet-secrets scripts/memory_client_original.py:68
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    print(f"   Recovery phrase: {data['recovery_phrase'][:50]}...")
    quoted
  • low Risky intent intent-wallet-secrets scripts/memory_client_original.py:69
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    print(f"\n⚠️  SAVE THIS RECOVERY PHRASE! It's your only way to recover your identity.")
    quoted
  • low Risky intent intent-wallet-secrets scripts/memory_client_original.py:73
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    """Recover agent identity from recovery phrase."""
    quoted
  • low Risky intent intent-wallet-secrets scripts/memory_client_original.py:208
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)
    recover_parser.add_argument("phrase", help="Recovery phrase")
    detector
  • low Risky intent intent-wallet-secrets scripts/memory_client.py:42
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    """Recover private key from recovery phrase."""
    quoted
  • low Risky intent intent-wallet-secrets scripts/memory_client.py:68
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    print(f"   Recovery phrase: {data['recovery_phrase'][:50]}...")
    quoted
  • low Risky intent intent-wallet-secrets scripts/memory_client.py:69
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    print(f"\n⚠️  SAVE THIS RECOVERY PHRASE! It's your only way to recover your identity.")
    quoted
  • low Risky intent intent-wallet-secrets scripts/memory_client.py:73
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    """Recover agent identity from recovery phrase."""
    quoted
  • low Risky intent intent-wallet-secrets scripts/memory_client.py:208
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)
    recover_parser.add_argument("phrase", help="Recovery phrase")
    detector
  • low Risky intent intent-wallet-secrets SELF_IMPROVEMENT_GUIDE.md:166
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    ./scripts/memory_client.py recover "your recovery phrase"
    quoted

Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 49/100

  • 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
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (agent-memory-improved) differs from the folder (persistent-private-agent-memory)
  • 100Tools and files. No external tools needed
  • 100Steps. 25 steps
  • 100Execution cost. Instruction body is 731 tokens
  • 100Running it twice. No mutating operations
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • 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
  • -31 of 4 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 172: enough signal without eating the budget
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 25 items
  • +4Has examples (3 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.