Security audit
Security checks for vulnerabilities and agentic risk
This is a read-only SentiSense financial data skill that uses an API key to query SentiSense endpoints and does not show hidden execution, persistence, trading, or destructive behavior.
Install only if you are comfortable giving SentiSense an API key-backed record of the market data requests you make, including tickers, searches, watchlists, and screener filters. Treat outputs as informational market data, not investment advice, and do not use it as a trading or order-execution tool.
The section 'What You Can Build' introduces broad use cases without any explicit trigger phrases, invocation boundaries, or exclusion conditions for when the skill should or should not be used. In a skill markdown file, this kind of open-ended capability description can lead an agent platform to invoke the skill for generic finance-related requests beyond the author's intended scope.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
| limit | int | No | 100 | Rows returned, capped at 500. Sits here, not inside plan |
curl -X POST "https://app.sentisense.ai/api/v1/screener/execute" \
-H "X-SentiSense-API-Key: $SENTISENSE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
The getting-started instruction encourages immediate use but does not specify the kinds of user requests that should trigger this skill. In a markdown skill description, such generic wording can contribute to ambiguous activation behavior if the host uses natural-language descriptions for routing.
No suspicious patterns detected.