Revenue Tracker
Analysis
The tracker is coherent as a revenue tool, but it asks the agent to automatically sync sensitive revenue data to Google Sheets, Notion, and Telegram, so it should be reviewed before install.
Findings (4)
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.
After every `record` command, the script: ... Outputs structured instructions → agent executes: Priority 1 → Google Sheets ... Priority 2 → Notion
Each revenue record can trigger agent-executed writes to external tools. The artifacts do not clearly require user confirmation, verify the exact destination account/database, or describe reversal controls.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
uses_agent_telegram: true ... optional_skills: - wesley-web-operator - virtual-desktop
The skill relies on the agent's existing Telegram, Google/web-operator, and virtual-desktop authority. That is purpose-aligned, but users should understand which account identity will perform the actions.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
After every revenue event, outputs structured instructions for the agent to update Google Sheets (via gog), Notion (via virtual-desktop) ... The agent sends Telegram alerts
Sensitive financial events are handed from the script to the agent and then to other skills/providers, but the artifacts do not define identity, permissions, redaction, or data-boundary checks for those handoffs.
AUDIT_LOG = Path("/workspace/AUDIT.md") ... LEARNINGS_LOG = Path("/workspace/.learnings/LEARNINGS.md")The skill persistently records audit and learning information that may be reused by future agent workflows. This is expected for the tracker, but the data can contain sensitive or incorrect business context.
