The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its ingestion of external, untrusted data for research.
Ingestion points: The agent reads client-provided X posts, brand guidelines, and competitor profiles scraped via mcp__firecrawl__firecrawl_scrape.
Boundary markers: Absent. The skill does not instruct the agent to use specific delimiters or to ignore instructions embedded in the external content.
Capability inventory: The skill's capabilities are limited to calling MCP tools (mcp__tasty_content__search_x, mcp__firecrawl__firecrawl_scrape) and writing text files to a local outputs/ directory.
Sanitization: No validation or sanitization processes for the ingested data are specified.
[NO_CODE]: This skill consists solely of instructions within SKILL.md and does not include any executable scripts, binaries, or software packages.

x-writer