crosspost
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill provides a Python code example in the
API Integrationsection that uses therequestslibrary to send data to an external endpoint (https://your-crosspost-service.example/api/posts). While intended as a template, network requests to non-standard domains represent a potential path for data exposure. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it is designed to ingest and adapt untrusted user content for distribution across various platforms.
- Ingestion points: User-provided text for social media posts (SKILL.md).
- Boundary markers: None identified; the skill directly processes the input content.
- Capability inventory: Performs network operations via HTTP POST requests and interacts with external platform APIs (X, LinkedIn, Threads, Bluesky).
- Sanitization: No sanitization, escaping, or validation of the input content is documented before it is sent to external services.
Audit Metadata