grow-followers
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill communicates with an external API at
https://xquik.com/api/v1to resolve user handles and fetch performance metrics. This involves transmitting user identifiers to an external service, which is the intended functionality of the vendor's platform. - [PROMPT_INJECTION]: The skill processes untrusted tweet text and engagement data which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Data enters the context from external accounts via the
/x/users/{id}/tweetsendpoint inSKILL.md. - Boundary markers: The skill documentation explicitly warns the agent not to treat any string as an instruction, though it does not define specific technical delimiters.
- Capability inventory: The skill is limited to read-only API access and does not have capabilities for file system modification, command execution, or autonomous posting.
- Sanitization: Metadata indicates prompt injection defense is active, though the specific sanitization methods for external tweet content are not detailed.
Audit Metadata