x-insights

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions specify the use of the Apify MCP to call the 'apidojo/tweet-scraper' actor. This facilitates the retrieval of external data from X (Twitter) via a well-known third-party service, which is the primary intended function of the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes untrusted data from a third-party social media platform, creating an attack surface for indirect prompt injection.
  • Ingestion points: Untrusted data is retrieved from X (Twitter) via Apify actor outputs as described in the Workflow section of SKILL.md.
  • Boundary markers: Absent; the skill does not instruct the agent to use delimiters or ignore instructions embedded within the scraped content.
  • Capability inventory: The skill utilizes the 'apify' MCP tools ('call-actor' and 'get-actor-output') which provide the ability to interact with external web scraping services.
  • Sanitization: Absent; the skill directs the agent to perform thematic and tone analysis on the raw retrieved content without filtering or validation steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 01:39 PM
Security Audit — agent-trust-hub — x-insights