SKILLEMALL.ai
GitHub ↗ RU Sign in

BC agentkey

Local, offline, encrypted API-key vault for agents: add/get/rotate/list keys, hash-chained audit log with tamper detection, staleness/expires reports, redacted inventory, fingerprints. Keys enter via stdin/0600-file (never argv), live at rest AES-256-CBC+PBKDF2(600k, OpenSSL) under ${AGENTKEY_HOME}/vault (0700/files 0600), tag-verified before decrypt (wrong pass = exit 4). NO network, NO telemetry, NO update beacon — keys never leave this machine.

ClawHub Agent Skills author: orionshaowswmw v2.0.0 MIT-0 10 files · 1 script body ≈ 592 tokens Open the sourceclawhub.ai↗ analyzed 22 h ago

Local, offline, encrypted API-key vault for agents: add/get/rotate/list keys, hash-chained audit log with tamper detection, staleness/expires reports…

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

IntegrationSecuritytype 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
B
88/100
safety, quality, tests
Safety 60%
95
Quality 40%
78
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
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.
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 · 5

✓ No critical or high findings

Medium and low: 5
  • low Secrets in code secret-high-entropy-token scripts/selftest.sh:12
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    chk "add stores ciphertext not plaintext" "python3 -c 'import subprocess,os,sys; s=os.environ[\"SBX\"]; key=b\"sk_l…789\"; p=subprocess.run([\"python3\",\"scripts/agentkey.py
    fixturequoted
  • low Secrets in code secret-high-entropy-token scripts/selftest.sh:14
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    chk "get returns exact key" "python3 -c 'import subprocess; p=subprocess.run([\"python3\",\"scripts/agentkey.py\",\"get\",\"openai\"],capture_output=True,text=True); assert p.returncode==0 and p.stdou
    fixturequoted
  • low Secrets in code secret-high-entropy-token scripts/selftest.sh:15
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    chk "fingerprint stable redacted" "python3 -c 'import subprocess,hashlib; k=b\"sk_l…789\"; fp=hash…256(k).hexdigest()[:16]; p=subprocess.run([\"python3\",\"scripts/agen
    fixturequoted
  • low Secrets in code secret-high-entropy-token scripts/selftest.sh:16
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    chk "list redacts key shows fp" "python3 -c 'import subprocess,hashlib; k=b\"sk_l…789\"; fp=hash…256(k).hexdigest()[:16]; p=subprocess.run([\"python3\",\"scripts/agentk
    fixturequoted
  • low Secrets in code secret-high-entropy-token scripts/selftest.sh:19
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    chk "put back good entry for later tests" "rm -f \"$AGENTKEY_HOME/vault/openai.enc.json\" && python3 -c 'import subprocess; p=subprocess.run([\"python3\",\"scripts/agentkey.py\",\"add\",\"openai\",\"-
    fixturequoted

Files scanned: 10. 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")
  • note frontmatter-key unknown frontmatter key "topics"

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
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 100Steps. 5 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 592 tokens
  • 100Running it twice. No mutating operations

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 451: enough signal without eating the budget
  • +4Structure: 4 headings
  • +3Step-by-step instructions: 5 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)
  • +3All 2 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.

External checks

ClawHub: suspicious
AgentKey is mostly a coherent offline API-key vault, but it includes an under-documented executable override that can hand the vault passphrase to an arbitrary local program if the environment is influenced.
LLM: suspicious (high) · 6 Sept 2026