pennydinh-marketing-pipeline-automation
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation instructs the agent to clone a repository from a personal GitHub account (github.com/pennydinh/marketing-pineline-share.git) to set up the automation system.
- [INDIRECT_PROMPT_INJECTION]: The skill implements an automated 'Research Module' that crawls untrusted external sources, including Twitter/X, LinkedIn, and various blogs. This data is directly used as context for generating AI content and scripts, creating an attack surface for indirect prompt injection.
- Ingestion points: The
ResearchCrawler(insrc/lib/research/crawler.ts) scans external sources including 'techcrunch', 'a16z', 'twitter', and 'linkedin'. - Boundary markers: The provided code snippets do not show any explicit boundary markers or instructions to the LLM to ignore potentially malicious content embedded in the crawled data.
- Capability inventory: The system is capable of writing files (video rendering) and publishing content to social media platforms (Facebook, LinkedIn) using provided access tokens.
- Sanitization: No sanitization, filtering, or validation of the crawled text data is shown before it is passed to the AI content generator.
Audit Metadata