The Agent Skills Directory

[COMMAND_EXECUTION]: The skill documents the use of the flarecrawl CLI tool alongside standard Unix utilities such as jq, grep, and cat. These tools are used for their intended purposes: mapping URLs, extracting data, filtering results, and creating configuration files (e.g., schema.json).
[INDIRECT_PROMPT_INJECTION]: The skill describes a process that ingests untrusted data from external websites via the flarecrawl extract command.
Ingestion points: Data enters the environment via the --urls and --batch flags in SKILL.md workflows.
Boundary markers: The skill encourages the use of structured JSON schemas (--schema, --schema-file) to constrain the AI's output shape, which serves as a defensive boundary against unstructured content.
Capability inventory: The skill uses the flarecrawl binary and standard shell tools for data processing.
Sanitization: Extraction relies on Cloudflare Workers AI schema validation to ensure the output matches the expected JSON format.

flarecrawl-extraction