twitter-scraper
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Twitter/X posts via the Apify actor
apidojo/tweet-scraper. - Ingestion Point:
scripts/search_twitter.pyfetches tweet content (textandfullTextfields) from the Apify dataset API. - Capability Inventory: The script performs network requests to
api.apify.comand outputs the results to stdout. It does not have file-write or arbitrary command execution capabilities. - Boundary Markers: The scraped data is returned to the agent as a structured JSON array or a text summary, which helps the agent distinguish between data and instructions.
- Sanitization: The script does not explicitly sanitize the tweet content for potential prompt injection patterns before returning it to the agent.
- [EXTERNAL_DOWNLOADS]: The script communicates with Apify's official API at
api.apify.comto trigger scraping tasks and retrieve results. Apify is a well-known web scraping platform.
Audit Metadata