marketing-pipeline-share-ai-content-automation

Warn

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires cloning and installing a repository from an unverified external source (github.com/pennydinh/marketing-pineline-share.git) that does not match the vendor's known infrastructure or trusted organization lists.
  • [PROMPT_INJECTION]: The skill creates a significant surface for indirect prompt injection by crawling external web content (Twitter, TechCrunch, etc.) and directly interpolating the results into AI prompts for content generation.
  • Ingestion points: External data fetched by the research crawler in src/research/crawler.
  • Boundary markers: Missing. Prompt templates shown in the examples (e.g., buildCustomPrompt) directly embed the JSON-stringified research data without delimiters or safety instructions.
  • Capability inventory: The skill performs network operations, interacts with paid LLM APIs (Claude, OpenAI), and writes video files to the local file system.
  • Sanitization: No validation or sanitization logic is present to filter malicious instructions embedded in crawled news articles or social media posts.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 29, 2026, 09:55 AM
Security Audit — agent-trust-hub — marketing-pipeline-share-ai-content-automation