discovery-explore
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from external sources on X (Twitter).
- Ingestion points: Data is pulled from
x.com/explore, search result pages, and user profiles through scripts likesrc/trendingTopicMonitor.jsandscripts/scrapeSearch.js. - Boundary markers: There are no defined boundary markers or instructions to ignore embedded commands within the scraped content.
- Capability inventory: The skill supports scanning, tracking trends, keyword monitoring, and exporting data to JSON.
- Sanitization: No sanitization, escaping, or validation of the ingested social media content is specified.
Audit Metadata