The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection because it ingests and processes untrusted data from external URLs.
Ingestion points: Web content retrieved from arbitrary URLs provided in the firecrawl scrape command (SKILL.md).
Boundary markers: No explicit instructions or delimiters are provided to the agent to treat the scraped content as untrusted data or to ignore embedded instructions.
Capability inventory: The skill has access to the Bash tool to execute shell commands and file system access to write scraped content to disk (SKILL.md).
Sanitization: There is no evidence of sanitization or filtering of the scraped content to remove potentially malicious markdown or hidden instructions before it is presented to the agent.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute firecrawl and firecrawl-cli commands. This includes running queries against web content and writing data to the local file system (e.g., .firecrawl/page.md).
[EXTERNAL_DOWNLOADS]: The skill configuration allows for the execution of npx firecrawl-cli, which downloads the firecrawl-cli package from the npm registry at runtime. This package is provided by the vendor 'firecrawl'.

firecrawl-scrape