social-media

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. It is designed to manage social media engagement, including automated or assisted responses to external comments and mentions.
  • Ingestion points: The reference.md file defines 'Engagement Rules' and 'Auto-Response' categories, indicating the agent will ingest and process untrusted data from social media platforms (LinkedIn, Twitter, Facebook, Instagram).
  • Boundary markers: There are no explicit instructions or delimiters provided to prevent the agent from obeying instructions embedded within processed social media comments.
  • Capability inventory: The skill has access to high-privilege tools including Bash, Write, Edit, and Grep (as defined in SKILL.md).
  • Sanitization: The provided Python script (scripts/generate_calendar.py) handles local file generation but does not include sanitization logic for external content that might be processed during engagement tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 10:43 PM
Security Audit — agent-trust-hub — social-media