linkedin-content
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates a workflow where external search data (via Tavily) is ingested and used to generate content for social media platforms. This creates a potential surface for indirect prompt injection if the source data contains malicious instructions designed to influence the AI's behavior.
- Ingestion points: Uses
tavily/search-assistantto research trending content patterns based on web search data (SKILL.md). - Boundary markers: No specific boundary markers or instructions to ignore embedded commands are defined for the search output processing.
- Capability inventory: The skill includes capabilities to post to external platforms (
x/post-create) and generate visual assets via image-generation tools. - Sanitization: No explicit sanitization or validation mechanisms are described for the external content before it is processed by the AI.
Audit Metadata