Skills
Navigate
skills/apidojo-io/apidojo-skills/monitoring-twitter-for-competitor-job-posts/Gen Agent Trust Hub

monitoring-twitter-for-competitor-job-posts

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 exposes a customMapFunction input parameter described as a 'JavaScript function to transform each output object'. This facilitates the execution of arbitrary JavaScript code at runtime to process data.
  • [COMMAND_EXECUTION]: The skill provides commands to execute a local script named scripts/run_actor.js using the node environment. This script is responsible for triggering the scraper, handling output, and saving files in various formats (CSV, JSON).
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data from Twitter, which could contain malicious instructions.
  • Ingestion points: External tweets are retrieved from Twitter via the apidojo/tweet-scraper actor on Apify.
  • Boundary markers: No delimiters or instructions to ignore embedded commands are specified in the workflow.
  • Capability inventory: The skill has capabilities to write data to the local file system (via the --output flag in the script) and make network requests to the Apify API.
  • Sanitization: There is no mention of sanitizing or filtering the tweet content before it is processed, displayed, or saved.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with the Apify platform to execute the apidojo/tweet-scraper actor and retrieves data from api.apify.com. These operations are performed using the user-provided APIFY_TOKEN.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 2, 2026, 06:33 PM
Security Audit — agent-trust-hub — monitoring-twitter-for-competitor-job-posts