linkedin-post-rewrite

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is purely instructional and does not contain any executable scripts, shell commands, or network operations. All instructions are focused on content transformation and formatting.
  • [INDIRECT_PROMPT_INJECTION]: The skill operates by processing external content (Substack essays), which creates an indirect prompt injection surface. This is a common characteristic of text-processing skills and no specific exploits were found.
  • Ingestion points: External essay content is ingested as the primary source for the rewrite task described in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or isolation markers for the input content.
  • Capability inventory: The skill directs the agent to generate a markdown file (linkedin-post.md), involving standard file system write capabilities.
  • Sanitization: There are no explicit sanitization or validation steps for the incoming essay data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 02:36 PM
Security Audit — agent-trust-hub — linkedin-post-rewrite