SKILLEMALL.ai
GitHub ↗ RU Sign in

DC crypto-executor-optimizer

Autonomous optimizer skill for Wesley — reads Binance trading performance every 6 hours, analyzes win rate and strategy metrics, then safely tunes executor.py parameters (OBI thresholds, Kelly factor, strategy mix) via backup → modify → validate → restart.

Not recommendedcritical or high security findings · low grade D
modbender/skill-library-mcp Agent Skills author: modbender MIT 5 files · 3 scripts body ≈ 2 280 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Autonomous optimizer skill for Wesley — reads Binance trading performance every 6 hours, analyzes win rate and strategy metrics, then safely tunes executor.py…

As a process C 50/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationTelegramGitHubSoftware developmenttype 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
D
53/100
safety, quality, tests
Safety 60%
41
Quality 40%
71
Run on models
none yet
Process rating
C
50/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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.
  2. 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 · 13

  • high Dangerous commands cmd-persistence install_cron.sh:48
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    (crontab -l 2>/dev/null | grep -v crypto-executor-optimizer; echo "# Wesley Optimizer") | crontab -
  • high Dangerous commands cmd-persistence install_cron.sh:49
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    (crontab -l 2>/dev/null; echo "$CRON_LINE") | crontab -
Medium and low: 11
  • medium Exfiltration net-credential-use apply_optimization.sh:195
    Credential used in a network call (verify the destination is the intended service)
    curl -s -X POST "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendMessage" \
  • medium Exfiltration net-credential-use apply_optimization.sh:254
    Credential used in a network call (verify the destination is the intended service)
    curl -s -X POST "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendMessage" \
  • medium Exfiltration exfil-webhook-url SKILL.md:56
    Webhook / callback URL commonly used for exfiltration (verify the destination) (detector / deny-list definition)
    - "https://api.telegram.org/bot*"
    detector
  • low Exfiltration exfil-webhook-url apply_optimization.sh:195
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    curl -s -X POST "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendMessage" \
    placeholder
  • low Dangerous commands cmd-background-process apply_optimization.sh:218
    Starts a background / autostarted process
    nohup python3 "$EXECUTOR_PATH" >> /workspace/logs/binance_bot.log 2>&1 &
  • low Exfiltration exfil-webhook-url apply_optimization.sh:254
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    curl -s -X POST "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendMessage" \
    placeholder
  • low Dangerous commands cmd-cron-mention install_cron.sh:48
    Mentions editing / listing crontab
    (crontab -l 2>/dev/null | grep -v crypto-executor-optimizer; echo "# Wesley Optimizer") | crontab -
  • low Dangerous commands cmd-cron-mention install_cron.sh:49
    Mentions editing / listing crontab
    (crontab -l 2>/dev/null; echo "$CRON_LINE") | crontab -
  • low Dangerous commands cmd-background-process setup_binance_20euros.sh:183
    Starts a background / autostarted process
    nohup python3 "$EXECUTOR_PATH" > /workspace/logs/binance_bot.log 2>&1 &
  • low Dangerous commands cmd-cron-mention SKILL.md:162
    Mentions editing / listing crontab (documentation table row)
    | `crontab -e` | Installer le job récurrent (fallback system cron) |
    table
  • low Dangerous commands cmd-cron-mention SKILL.md:295
    Mentions editing / listing crontab
    crontab -e  # supprimer la ligne crypto-executor-optimizer

Files scanned: 5. 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 50/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 1 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 100Steps. 43 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2280 tokens
  • 100Progress reporting. Reports progress

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
  • -222 emoji in the instructions: noise for the model
  • +2Single-language instructions
  • +3Description length 256: enough signal without eating the budget
  • +4Structure: 20 headings
  • +3Step-by-step instructions: 43 items
  • +4Has examples (11 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.