Firecrawl Skill Security Audit

1718This installs `firecrawl-cli` globally, authenticates via browser, and installs core and workflow skills. Build skills are a separate step: `firecrawl setup build`.19

2728Skills are installed globally across all detected coding editors by default.29

118  --tags docs \119  --note "The pricing table was missing from the markdown output." \120  --url "https://example.com/pricing" \121  --page-numbers 1 \122  --silent &123```

124125Keep generic feedback small: issue codes, tags, short notes, URLs, page numbers, and small metadata objects — never raw scrape/parse outputs or full page contents.126127**Opt out:** `export FIRECRAWL_NO_ENDPOINT_FEEDBACK=1` makes the CLI skip every endpoint feedback call silently. Respect that flag — do not try to work around it.128

114```bash115firecrawl feedback scrape "$SCRAPE_ID" \116  --rating partial \117  --issues missing_markdown \118  --tags docs \119  --note "The pricing table was missing from the markdown output." \120  --url "https://example.com/pricing" \121  --page-numbers 1 \122  --silent &123```

16- **Gitignored output**: `.firecrawl/` is added to `.gitignore` so fetched content is never committed to version control.17- **User-initiated only**: All web fetching is triggered by explicit user requests. No background or automatic fetching occurs.18- **URL quoting**: Always quote URLs in shell commands to prevent command injection.

5152`--status` shows auth state, concurrency (max parallel jobs — run parallel operations up to that limit), and remaining API credits.53

1314- **File-based output isolation**: All commands use `-o` to write results to `.firecrawl/` files rather than returning content directly into the agent's context window. This avoids overflowing the context with large web pages.15- **Incremental reading**: Never read entire output files at once. Use `grep`, `head`, or offset-based reads to inspect only the relevant portions, limiting exposure to injected content.16- **Gitignored output**: `.firecrawl/` is added to `.gitignore` so fetched content is never committed to version control.17- **User-initiated only**: All web fetching is triggered by explicit user requests. No background or automatic fetching occurs.

41| AI-powered data extraction  | `agent`               | Need structured data from complex sites                         |42| Interact with a page        | `scrape` + `interact` | Content requires clicks, form fills, pagination, or login       |43| Download a site to files    | `x download`          | Save an entire site as local files                              |

53- Use `scrape` first. It handles static pages and JS-rendered SPAs.54- Use `scrape` + `interact` when you need to interact with a page, such as clicking buttons, filling out forms, navigating through a complex site, infinite scroll, or when scrape fails to grab all the content you need.55- For web searches, use `search` — interact is for acting on a specific page.

5253- Use `scrape` first. It handles static pages and JS-rendered SPAs.54- Use `scrape` + `interact` when you need to interact with a page, such as clicking buttons, filling out forms, navigating through a complex site, infinite scroll, or when scrape fails to grab all the content you need.55- For web searches, use `search` — interact is for acting on a specific page.56

72- **AI-powered structured extraction from complex sites** -> [firecrawl-agent](../firecrawl-agent/SKILL.md)73- **Clicks, forms, login, pagination, or post-scrape browser actions** -> [firecrawl-interact](../firecrawl-interact/SKILL.md)74- **Downloading a site to local files** -> [firecrawl-download](../firecrawl-download/SKILL.md)

1314```bash15npx -y firecrawl-cli@latest init -y --browser16```17