monitoring-instagram-hashtag-trends

Warn

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: MEDIUMDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill defines a 'customMapFunction' input parameter that accepts a JavaScript function as a string for transforming output objects, which introduces a dynamic code execution surface.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from external Instagram URLs (profiles, hashtags, reels) that may contain malicious instructions intended for the agent. • Ingestion points: Instagram post data, captions, and comments scraped via the Apify actor. • Boundary markers: No specific delimiters or safety instructions are used to separate user data from instructions. • Capability inventory: Subprocess execution through 'node' and 'curl' commands, and the ability to write result files to the local file system. • Sanitization: No explicit content filtering or sanitization of the scraped data is mentioned.
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute shell commands using 'node' for a local script (scripts/run_actor.js) and 'curl' for API interaction, which are essential to its intended functionality.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 2, 2026, 07:00 PM
Security Audit — agent-trust-hub — monitoring-instagram-hashtag-trends