social-calendar-system

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill mentions triggering Playwright-driven QA processes to verify landing page links. While this involves browser automation, it is presented as a legitimate functional guardrail for marketing operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process social media performance data and sentiment analysis results. While these are external inputs, the skill provides a template for human-in-the-loop review and structured reporting, which reduces the risk of automated instruction bypass.
  • [SAFE]: The skill utilizes standard business logic for content approvals and performance guardrails. References to platforms like LinkedIn, X (formerly Twitter), and TikTok, as well as tools like Playwright, are consistent with the stated purpose of a social calendar system.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 12:49 AM
Security Audit — agent-trust-hub — social-calendar-system