The Agent Skills Directory

[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests untrusted data from arbitrary competitor websites. Ingestion points: Scraped content retrieved via firecrawl_scrape and firecrawl_map (SKILL.md). Boundary markers: The instructions do not specify the use of delimiters or 'ignore' commands to isolate external web content from the agent's core instructions. Capability inventory: The agent is authorized to write synthesized markdown reports and raw data files to the competitor-profiles/ directory in the project root (SKILL.md). Sanitization: No explicit validation or filtering logic is defined for the scraped content before it is processed into the final synthesized output.
[EXTERNAL_DOWNLOADS]: The skill utilizes well-known technology services for data acquisition. It fetches website structure and content via Firecrawl and retrieves SEO metrics through DataForSEO (references/tool-reference.md).
[SAFE]: File system access is restricted to reading non-sensitive marketing context files and writing structured research data to a dedicated project sub-directory.

competitor-profiling