x-twitter-monitor
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill makes network requests to
twitr.shto monitor Twitter accounts and keywords. This is the primary intended functionality of the skill. - [DATA_EXFILTRATION]: No sensitive local data or credentials are accessed or transmitted. The skill uses an external payment protocol (x402/MPP) for billing, which avoids the need for hardcoded API keys or personal credentials.
- [PROMPT_INJECTION]: No evidence of instructions attempting to override agent behavior or bypass safety filters was found.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external source (Twitter/X posts via the twitr.sh API).
- Ingestion points: Data is received through polling the
/api/monitors/{id}/eventsendpoint and via webhook deliveries. - Boundary markers: The instructions do not provide explicit boundary markers or guidance to the agent on how to handle potentially malicious text within the retrieved tweets.
- Capability inventory: The skill's primary capability is network communication with the vendor's API.
- Sanitization: No sanitization or filtering of the retrieved social media content is mentioned in the skill definition.
Audit Metadata