ai-content-pipeline-automation
Warn
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to clone a repository from
https://github.com/pennydinh/marketing-pineline-share.git. This source belongs to an unverified account not associated with a trusted organization or the skill author. - [COMMAND_EXECUTION]: The automation setup involves running
npm installandnpm run devon the cloned repository, which executes third-party code with the permissions of the local environment. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external websites that could influence agent behavior. 1. Ingestion points: Content is scraped from sources like TechCrunch and Twitter via
scrapeNewsArticles. 2. Boundary markers: Data is concatenated into the prompt using newlines without specific delimiters or instructions to ignore embedded commands. 3. Capability inventory: The skill generates content and triggers video rendering through Remotion. 4. Sanitization: No sanitization is performed on the scraped content beyond simple truncation.
Audit Metadata