x-audience-insights

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content from X (Twitter), which could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: Untrusted data enters the context through the fetch_user_tweets and fetch_tweet_replies methods described in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the processed tweets or replies.
  • Capability inventory: The skill's primary capabilities are limited to data analysis, pattern extraction, and report generation; it lacks high-risk tools for file modification or system command execution.
  • Sanitization: The skill does not implement validation or filtering for the external data it processes.
  • [SAFE]: The skill integrates with Apify's official services for data retrieval, which is a well-known and legitimate cloud service.
  • [SAFE]: The skill follows security best practices by instructing users to manage sensitive API tokens through environment variables rather than hardcoding them.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 05:43 PM
Security Audit — agent-trust-hub — x-audience-insights