SKILLEMALL.ai
GitHub ↗ RU Sign in

BC sparkey

Time-limited, self-destructing SSH access for AI agents. Four-layer defense-in-depth: certificate TTL, OS account expiry, command-restricted dispatch, and automated cleanup. Zero session artifacts survive.

ClawHub Agent Skills author: Neo v1.2.1 MIT-0 8 files · 4 scripts body ≈ 6 030 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 59/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice

ProcedureAI and agentsInfrastructuretype 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
79/100
safety, quality, tests
Safety 60%
88
Quality 40%
66
Run on models
none yet
Process rating
C
59/100
Has gaps
Result and completion w 14
0
When it triggers w 12
20
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 12

✓ No critical or high findings

Medium and low: 12
  • low Dangerous commands cmd-privilege README.md:49
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo bash scripts/setup-ca.sh
    security skill
  • low Dangerous commands cmd-privilege README.md:52
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo bash scripts/grant-access.sh \
    security skill
  • low Dangerous commands cmd-privilege README.md:58
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo bash scripts/revoke-access.sh --session SESSION_ID
    security skill
  • low Dangerous commands cmd-privilege scripts/audit.sh:117
    Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)
    printf 'To clean up all sessions: sudo bash scripts/revoke-access.sh --all\n'
    code literalsecurity skill
  • low Dangerous commands cmd-privilege scripts/grant-access.sh:629
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    printf '    sudo bash %s\n' "${cleanup_script}"
    code literal
  • low Dangerous commands cmd-privilege scripts/grant-access.sh:670
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    printf '    sudo bash scripts/revoke-access.sh --session %s\n' "${session_id}"
    code literal
  • low Dangerous commands cmd-privilege SKILL.md:154
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo bash scripts/setup-ca.sh
    security skill
  • low Dangerous commands cmd-privilege SKILL.md:157
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo bash scripts/grant-access.sh --host TARGET_HOST --duration 4h --agent-pubkey /path/to/agent_key.pub --dry-run
    security skill
  • low Dangerous commands cmd-privilege SKILL.md:160
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo bash scripts/grant-access.sh --host TARGET_HOST --duration 4h --agent-pubkey /path/to/agent_key.pub
    security skill
  • low Dangerous commands cmd-privilege SKILL.md:163
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo bash scripts/grant-access.sh --host TARGET_HOST --duration 4h --allow diagnostic
    security skill
  • low Dangerous commands cmd-privilege SKILL.md:166
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo bash scripts/revoke-access.sh --session SESSION_ID
    security skill

A further 1 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 frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Time-limited, self-destructing SSH access for AI agents. Four-laye… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
  • warning body-long SKILL.md body ≈ 6030 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "files"

Process rating: all ten parameters 59/100

  • 0Result and completion. Does not say what the result is
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 20 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 6030 tokens
  • 85Steps. 79 steps, 1 vague phrases
  • 100Failures and branches. 14 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 13 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
  • +2Single-language instructions
  • +3Description length 205: enough signal without eating the budget
  • +4Structure: 35 headings
  • +3Step-by-step instructions: 79 items
  • +4Has examples (22 code blocks)
  • +3All 4 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.

External checks

ClawHub: suspicious
Sparkey is a real temporary SSH-access tool, but it needs review because it uses root-level account and SSH authority while some security claims and host-scoping are under-disclosed.
LLM: suspicious (high) · VirusTotal: · 29 May 2026