analytics-expert
Warn
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Recommends the installation of an external plugin from an unverified third-party GitHub repository (coreyhaines31/marketingskills) via the /plugin marketplace add command. This represents a supply chain risk as the repository is not from a recognized trusted organization or service.
- [PROMPT_INJECTION]: The skill processes external content analytics data that could be used for indirect prompt injection.
- Ingestion points: Aggregates performance metrics and engagement data, including comments and shares, which are potentially attacker-controlled (SKILL.md).
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external analytics data as untrusted or to ignore embedded instructions.
- Capability inventory: The skill is used to generate comprehensive reports and provide optimization recommendations, creating opportunities for malicious instructions in data to influence agent behavior.
- Sanitization: No sanitization, validation, or escaping logic is described for the data retrieved from external platforms.
Audit Metadata