web-scraper
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary function is web scraping, which requires network access to external sites and the installation of the 'crawl4ai' dependency as documented in 'SKILL.md'.
- [PROMPT_INJECTION]: The skill ingests untrusted data from external websites, creating a surface for indirect prompt injection.
- Ingestion points: Untrusted content is fetched via 'AsyncWebCrawler.arun' across 'SKILL.md', 'EXAMPLES.md', and 'PATTERNS.md'.
- Boundary markers: Absent; scraped content is not wrapped in protective delimiters or accompanied by instructions to ignore embedded commands.
- Capability inventory: The skill is granted 'Bash', 'Read', 'Write', and 'Edit' tools in 'SKILL.md', enabling script execution and file system modifications via the agent.
- Sanitization: Absent; the skill extracts text content without filtering for potentially malicious instructions.
Audit Metadata