scraping-urban-dictionary-definitions

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted, crowd-sourced content from Urban Dictionary which could potentially contain malicious instructions intended for the AI agent.
  • Ingestion points: The definition, example, and author fields in the scraped output (SKILL.md).
  • Boundary markers: None present; content is returned as raw strings without delimiters.
  • Capability inventory: The skill utilizes shell commands via node and curl to interact with the Apify API.
  • Sanitization: No sanitization or filtering of the scraped content is performed within the skill definition.
  • [DYNAMIC_EXECUTION]: The skill supports a customMapFunction input parameter which accepts a JavaScript string to be executed on the Apify platform for data transformation.
  • [COMMAND_EXECUTION]: The documentation provides examples for running shell commands (node scripts/run_actor.js and curl) that incorporate user-supplied input parameters.
  • [EXTERNAL_DOWNLOADS]: The skill connects to the Apify REST API (api.apify.com) and utilizes a remote scraper actor (apidojo/urbandictionary-scraper) to perform its primary function.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 06:27 PM
Security Audit — agent-trust-hub — scraping-urban-dictionary-definitions