blog-to-linkedin-post

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a highly structured and professional workflow for content repurposing. It implements validation steps (minimum word count), source normalization (removing navigation/boilerplates), and data-to-insight mapping (spine extraction).
  • [SAFE]: External references are limited to official LinkedIn help documentation and reputable industry news for trend analysis. All browsing operations are context-specific and necessary for the primary function of the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided blog content.
  • Ingestion points: User-provided blog text, Markdown, HTML, or URLs are processed in the 'Input Handling' and 'Mandatory Workflow' sections.
  • Boundary markers: The skill does not explicitly use specific delimiters to wrap input text, but it uses a rigorous extraction process (Step 2: Article Spine) that maps input to specific fields like 'Topic' and 'Evidence', which naturally mitigates broad injection attempts.
  • Capability inventory: The skill uses web browsing to fetch articles and trend information.
  • Sanitization: The skill involves normalizing the source and separating facts from interpretation, though it does not explicitly filter for embedded commands.
  • Risk Assessment: Given the structured extraction workflow, the risk of the agent obeying commands hidden within a blog post is low.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 06:00 PM
Security Audit — agent-trust-hub — blog-to-linkedin-post