x-writer
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill functions as a content creation assistant, adhering to its stated purpose. It accesses local context files like
brand-style.mdandcontent-calendar.mdand writes generated content tooutputs/x/. These operations are well-scoped and do not involve sensitive system paths or unauthorized network activity. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, creating a potential attack surface.
- Ingestion points: External data enters the context via
mcp__firecrawl__firecrawl_scrapewhen analyzing competitor X profiles (SKILL.md). - Boundary markers: Instructions do not mandate delimiters or warnings to ignore instructions within the scraped content.
- Capability inventory: The skill is capable of executing MCP tools and writing output to the
outputs/x/directory (SKILL.md). - Sanitization: No explicit sanitization or filtering of the scraped content is performed before interpolation.
Audit Metadata