The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the firecrawl-pp-cli and firecrawl-pp-mcp binaries from the author's repository and NPM package scope.
Evidence: npx -y @mvanhorn/printing-press install firecrawl --cli-only (SKILL.md)
Evidence: go install github.com/mvanhorn/printing-press-library/library/developer-tools/firecrawl/cmd/firecrawl-pp-cli@latest (SKILL.md)
[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to install dependencies and run the scraping CLI tool.
Evidence: Numerous commands starting with firecrawl-pp-cli throughout SKILL.md.
[DATA_EXFILTRATION]: The tool supports an output delivery feature that can POST data to a remote URL, which represents a potential data exfiltration capability.
Evidence: Support for webhook:<url> in the --deliver parameter (SKILL.md).
[PROMPT_INJECTION]: The skill facilitates the scraping and processing of external web content using LLMs, which introduces a surface for indirect prompt injection.
Ingestion points: Scraped content retrieved from external URLs via scrape, crawl, map, and extract commands (SKILL.md).
Boundary markers: The instructions do not define delimiters or warnings to prevent the agent from following instructions embedded in the scraped data.
Capability inventory: The agent has access to file writing (file:<path>), command execution (firecrawl-pp-cli), and network POSTing (webhook:<url>).
Sanitization: No sanitization or validation of the retrieved web content is specified before it is processed by the agent.

pp-firecrawl