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-assistant to 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
Risk Level
SAFE
Analyzed
Sep 21, 2026, 08:14 PM
Security Audit — agent-trust-hub — linkedin-content