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.mdfile 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, andGrep(as defined inSKILL.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