playbook-social-posts

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes social media content from external LinkedIn profiles, which represents a potential attack surface for indirect prompt injection where malicious text in a post could influence the AI-generated output.
  • Ingestion points: LinkedIn post content is scraped via the Apify tool and processed in the workflow nodes, specifically Node 8 of clay-workflow.md.
  • Boundary markers: The skill lacks explicit delimiters or instructions to the AI agent to disregard potential commands embedded within the scraped social media text.
  • Capability inventory: The risk is limited as the agent's capabilities are restricted to generating a text string for personalization, without access to high-privilege system commands or external network write operations.
  • Sanitization: A mandatory skip filter is implemented to exclude content based on sensitive categories like politics or bereavement, providing a layer of content moderation.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the Apify platform via the apify-run-actor tool to perform its scraping functions. This is a standard integration with a well-known third-party automation service.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 02:36 PM
Security Audit — agent-trust-hub — playbook-social-posts