web-crawler
Pass
Audited by Gen Agent Trust Hub on May 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection because it is designed to fetch and process untrusted data from social media posts, web pages, and video transcripts into the agent's context.
- Ingestion points: Data is retrieved from arbitrary external URLs and platforms such as TikTok, Instagram, and YouTube via the ScrapeCreators and Firecrawl APIs.
- Boundary markers: The instructions do not define clear delimiters or specialized prompts to ensure the agent distinguishes between fetched data and its own operational instructions.
- Capability inventory: The skill utilizes Python-based network request helpers (proxied_get, proxied_post) to interact with remote services.
- Sanitization: The skill does not implement specific sanitization, filtering, or validation of the fetched content before presenting it to the agent for analysis.- [SAFE]: The skill interacts with external APIs at scrapecreators.com and firecrawl.dev to perform its stated crawling functions. These are vendor-provided services for this skill and do not involve unauthorized data exfiltration or sensitive file access.
Audit Metadata