x-scraper
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use
curlandjqto interact with the Apify API for starting tasks, polling status, and fetching results. - [EXTERNAL_DOWNLOADS]: The skill fetches data from
api.apify.com, which is a well-known service for web scraping and automation. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing untrusted data from X (Twitter). \n
- Ingestion points: Tweet text and metadata retrieved from the Apify API. \n
- Boundary markers: Absent. There are no instructions for the agent to treat retrieved tweet content strictly as data rather than potential instructions. \n
- Capability inventory: CLI execution (
curl,jq) and network access. \n - Sanitization: None. The skill does not provide mechanisms to sanitize or validate the content of the scraped tweets before processing.
Audit Metadata