linkedin-post-writing

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information such as topics, viewpoints, and experience to generate post drafts. This represents a potential surface for instructions hidden in user input. However, the skill has no tool-use capabilities, file-writing permissions, or network access beyond providing informational links, which limits the potential impact to the generated text content.
  • Ingestion points: Step 1 of workflows/draft-linkedin-post.md captures audience, topic, and asset inputs.
  • Boundary markers: The skill does not define specific delimiters for separating user content from instructions.
  • Capability inventory: The skill is restricted to text generation; no system tools or shell commands are invoked.
  • Sanitization: No specific validation or filtering logic is applied to input strings.
  • [EXTERNAL_DOWNLOADS]: The skill includes several references to official LinkedIn help articles in references/core/knowledge.md. These links are provided for manual user reference regarding platform character limits, scheduling, and policy information.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 01:03 AM
Security Audit — agent-trust-hub — linkedin-post-writing