SKILLEMALL.ai
GitHub ↗ RU Sign in

FC clawseal

Cryptographic memory for AI agents with QSEAL tamper-evidence. Zero-config demo mode, scroll-native YAML storage.

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: Shawn Cohen v1.0.3 MIT-0 9 files · 1 script body ≈ 1 139 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

ProcedureInfrastructureAI 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
F
31/100
safety, quality, tests
Safety 60%
0
Quality 40%
78
Run on models
none yet
Process rating
C
59/100
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

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
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 · 11

  • high Dangerous commands cmd-persistence install.sh:73
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load "$PLIST_PATH"
  • high Dangerous commands cmd-persistence OPENCLAW_INTEGRATION.md:217
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl unload ~/Library/LaunchAgents/com.mvar.clawseal.plist
  • high Dangerous commands cmd-persistence OPENCLAW_INTEGRATION.md:218
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load ~/Library/LaunchAgents/com.mvar.clawseal.plist
  • high Dangerous commands cmd-persistence README.md:99
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl unload ~/Library/LaunchAgents/com.mvar.clawseal.plist
  • high Dangerous commands cmd-persistence README.md:100
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load ~/Library/LaunchAgents/com.mvar.clawseal.plist
  • high Dangerous commands cmd-persistence README.md:119
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl unload ~/Library/LaunchAgents/com.mvar.clawseal.plist
  • high Dangerous commands cmd-persistence README.md:122
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load ~/Library/LaunchAgents/com.mvar.clawseal.plist
Medium and low: 4
  • medium Dangerous commands cmd-persistence install.sh:40
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    PLIST_PATH="$HOME/Library/LaunchAgents/com.mvar.clawseal.plist"
    code literal
  • medium Dangerous commands cmd-persistence install.sh:146
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    echo "  Stop:  launchctl unload ~/Library/LaunchAgents/com.mvar.clawseal.plist"
    code literal
  • medium Dangerous commands cmd-persistence install.sh:147
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    echo "  Start: launchctl load ~/Library/LaunchAgents/com.mvar.clawseal.plist"
    code literal
  • medium Dangerous commands cmd-persistence README.md:114
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    - **Service file**: `~/Library/LaunchAgents/com.mvar.clawseal.plist`
    quoted

Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 59/100

  • 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
  • 70When it triggers. States when to use, but not when not to
  • 100Tools and files. No external tools needed
  • 100Steps. 20 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1139 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

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)
  • +3Description length 113: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 20 items
  • +4Has examples (11 code blocks)

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

External checks

ClawHub: suspicious
ClawSeal appears to provide the advertised signed memory feature, but it also installs an always-on local memory server with weak access controls and automatic persistence.
LLM: suspicious (high) · VirusTotal: · 29 May 2026