market-social
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill logic is focused on text generation and strategy formulation. It operates on local project files and outputs to a standard markdown file, demonstrating no malicious intent or suspicious activities.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface that could be targeted by indirect prompt injection from third-party websites. \n
- Ingestion points: Untrusted data enters the context through the
topic/urlinput defined inSKILL.md. \n - Boundary markers: The instructions lack explicit delimiters or warnings to disregard instructions potentially embedded in the fetched URL content. \n
- Capability inventory: The skill's capabilities are restricted to reading internal reference markdown files and writing the final report to
SOCIAL-CALENDAR.md. No high-risk tools such as subprocess execution or network requests are utilized. \n - Sanitization: No automated sanitization of the input URL content is specified in the workflow.
Audit Metadata