marketing-pipeline-ai-content
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to clone an external repository (https://github.com/pennydinh/marketing-pineline-share.git) and install its dependencies. This repository is not from a verified or well-known organization.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to the way it handles external data.
- Ingestion points: Untrusted data is fetched from sources like TechCrunch, Twitter/X, and LinkedIn via the
crawlResearchmodule. - Boundary markers: Absent. The prompt template in the
createContentfunction directly interpolates the research data usingJSON.stringifywithout any delimiters or instructions to ignore embedded commands. - Capability inventory: The system can perform network operations (API calls) and execute subprocesses through the Remotion rendering engine (
renderMedia). - Sanitization: Absent. There is no evidence of validation or filtering for the fetched research content before it is included in the prompt to the language model.
Audit Metadata