Charts
Analysis
The charting workflow is mostly coherent, but it includes a hard-coded Telegram send target and depends on an unprovided local Python helper.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
Uses the local `crypto_charts.py` module.
The reviewed package is instruction-only and does not include this referenced helper module, so the charting and cleanup behavior depends on local code outside the supplied artifacts.
cd ~/clawd && python3 -c " import json from crypto_charts import generate_all_charts, cleanup_old_charts cleanup_old_charts() report = generate_all_charts(...)
The intended workflow runs local Python commands and invokes helper functions. This is expected for a chart-generation skill, but it is still local code execution.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
After generating, send the chart image using Clawdbot's native `message` command: ``` message (Telegram, target="7887978276") [attach ~/clawd/charts/chart_btc.png] ```
The skill includes an external messaging action to a fixed Telegram recipient, without requiring the installing user to select or confirm that destination.
