crosspost
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of text-based instructions and metadata. No malicious scripts, unauthorized network connections, or sensitive data access patterns were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill acts on user-provided text to generate social media variants. This ingestion of external data is a standard surface for indirect prompt injection; however, the skill has no dangerous capabilities (no file writes, no shell execution, no network operations), rendering the risk negligible. Ingestion points: User-provided source content in SKILL.md; Boundary markers: None; Capability inventory: None; Sanitization: None.
Audit Metadata