blotato
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted user data for social media publishing. Ingestion points: User-provided post content and media metadata in SKILL.md. Boundary markers: Instructions lack explicit delimiters or specific warnings to treat user content as data only. Capability inventory: The skill has the ability to publish content and list accounts on external social media platforms (Instagram, LinkedIn, Twitter/X, etc.). Sanitization: There is no evidence of input sanitization or validation for the content being published.
Audit Metadata