Sentiment Tracker
PassAudited by ClawScan on May 10, 2026.
Overview
This instruction-only skill is purpose-aligned, but users should notice that it can store ongoing local tracking data, use public web searches, and optionally set up scheduled monitoring.
This looks safe to install as an instruction-only sentiment tracker. Before enabling ongoing monitoring, confirm the tracked entities, search terms, schedule, alert thresholds, and delivery channel. Avoid monitoring confidential topics or private names unless you are comfortable with those terms being sent as web searches, and review ~/sentiment-analysis/ periodically.
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.
Your searched entity names, keywords, and visited public-post URLs may be sent to search or web-fetch providers.
The skill discloses use of external web search and fetch tools to gather public mentions, which is expected for sentiment tracking but means search queries and URL requests leave the machine.
| Search engines (via web_search) | Query text | Find mentions |
Use this only for topics you are comfortable searching publicly, and avoid putting private or confidential terms into monitored keywords.
Tracking preferences and activation choices may persist across sessions and influence when the skill is used later.
The skill asks the agent to store user preferences in persistent memory for future sessions. This is useful for monitoring, but persistent memory can affect future agent behavior.
Save their answer to their MAIN memory so other sessions know when to activate this skill.
Confirm what gets saved, periodically review the sentiment-analysis memory files and main memory, and remove or pause monitoring entries you no longer want.
If enabled, the skill may keep checking sentiment and producing alerts on a schedule.
The skill supports scheduled recurring monitoring. This is disclosed and matches the product purpose, but scheduled work is persistent behavior that can continue after setup.
For ongoing tracking, use cron. Default schedules: - **Critical entities**: Daily at 09:00 - **Regular entities**: Every 3 days - **Background entities**: Weekly
Only enable scheduled monitoring after confirming the entities, frequency, alert thresholds, delivery channel, and how to pause or remove the schedule.