linkedin-carousels

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's primary function is to provide structured instructions for designing LinkedIn carousel slides. It does not perform network operations or access sensitive system files.
  • [COMMAND_EXECUTION]: A local shell script (scripts/verify.sh) is included to lint the generated carousel specifications. It uses standard POSIX commands (grep, awk, find) for read-only static analysis of local markdown/text files. It does not exhibit behavior related to persistence or privilege escalation.
  • [PROMPT_INJECTION]: The skill includes instructions to process external source material (articles, blog posts) to create carousels. While this creates a surface for indirect prompt injection, the attack surface is minimal as the output is purely text-based design specifications.
  • Ingestion points: SKILL.md (source articles/posts provided by the user).
  • Boundary markers: Absent.
  • Capability inventory: Text generation and read-only local script execution.
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 09:37 PM
Security Audit — agent-trust-hub — linkedin-carousels