tracking-product-launch-buzz-on-twitter

Warn

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: MEDIUMDYNAMIC_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill defines an input parameter customMapFunction which accepts a JavaScript function as a string to transform output objects. Executing code provided as a runtime input parameter is a significant security risk if the input source is not strictly controlled.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using node to run a local script (scripts/run_actor.js) and curl to interact with the Apify REST API. This gives the agent direct access to the host shell environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from external social media sources.
  • Ingestion points: Fetches tweet content and metadata from Twitter via the apidojo/tweet-scraper actor.
  • Boundary markers: No delimiters or instructions are present to prevent the agent from interpreting ingested tweet content as new instructions.
  • Capability inventory: The skill has access to shell execution (node, curl) and dynamic JavaScript execution (customMapFunction).
  • Sanitization: The instructions do not define any sanitization or validation logic for the content fetched from the external API.
  • [EXTERNAL_DOWNLOADS]: The skill communicates with the Apify API (api.apify.com) to run scrapers and retrieve datasets. These interactions are consistent with the skill's purpose and target a well-known service infrastructure.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 2, 2026, 07:05 PM
Security Audit — agent-trust-hub — tracking-product-launch-buzz-on-twitter