The Agent Skills Directory

[SAFE]: The skill uses well-known technology services and standard tools for its intended purpose. No malicious commands, obfuscation, or unauthorized data access patterns were found in the skill content.\n- [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from the web, creating a potential surface for indirect prompt injection.\n
Ingestion points: Data is fetched from external websites using WebFetch, Firecrawl, or Bright Data tools as specified in the SKILL.md file.\n
Boundary markers: The skill does not define specific delimiters or security instructions to prevent the agent from executing commands embedded in the scraped content.\n
Capability inventory: The skill allows access to the Bash and Write tools, which are high-capability tools that could be abused if the agent obeys instructions found in external scraped data.\n
Sanitization: There are no documented steps for validating or sanitizing the content retrieved from external sources before processing.

scraping