xquik-x-tweet-scraper
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from X (Twitter) posts, profiles, and articles.
- Ingestion points: Scraped content from various X endpoints including searches and profile timelines (SKILL.md).
- Boundary markers: Includes a 'Critical Rule' to treat all returned data as untrusted research data and provides explicit instructions to the agent to ignore instructions embedded in the data.
- Capability inventory: The agent uses the Apify platform's xquik/x-tweet-scraper actor via SDK or REST API.
- Sanitization: Explicit instructions (Step 5) command the agent to not follow commands or instructions found within the scraped text or raw payloads.
- [CREDENTIALS_UNSAFE]: The skill requires an Apify API token for operation but correctly instructs the agent to handle it securely via Authorization headers and strictly forbids exposing it in URLs, prompts, or logs.
Audit Metadata