pennydinh-marketing-pipeline-automation

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires cloning a repository from https://github.com/pennydinh/marketing-pineline-share.git and installing dependencies. This involves executing code and packages from an external source not verified as a trusted vendor.\n- [PROMPT_INJECTION]: The skill's research module ingests content from external sources such as Twitter, LinkedIn, and TechCrunch to generate scripts and videos. This introduces a surface for indirect prompt injection attacks where malicious data could influence the generated content.\n
  • Ingestion points: Data is crawled from various social media and news platforms in src/lib/research/crawler.ts.\n
  • Boundary markers: No explicit safety instructions or delimiters to isolate untrusted external content were identified in the snippets.\n
  • Capability inventory: The skill uses AI for content generation and has the ability to render videos and potentially publish them to social platforms.\n
  • Sanitization: No sanitization or validation of the ingested external content is mentioned in the provided documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 07:44 PM
Security Audit — agent-trust-hub — pennydinh-marketing-pipeline-automation