finding-instagram-creators-by-location

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Instagram, such as post captions and user bios, to score creators. This creates a surface where malicious instructions embedded in social media content could potentially influence the agent's behavior during analysis. \n
  • Ingestion points: Instagram location posts via the apidojo/instagram-location-scraper actor (SKILL.md). \n
  • Boundary markers: No specific delimiters or 'ignore' instructions are defined to separate external data from agent instructions. \n
  • Capability inventory: File system access for writing CSV/JSON results, network access to Apify, and execution of local node scripts. \n
  • Sanitization: No explicit sanitization or filtering of the scraped Instagram content is mentioned before it is processed by the agent. \n- [DYNAMIC_EXECUTION]: The skill accepts a customMapFunction parameter, which is a JavaScript string used to transform data. While this code is executed remotely on the Apify platform, it involves the dynamic handling of executable code strings. \n- [COMMAND_EXECUTION]: The documentation references the execution of a local file scripts/run_actor.js using Node.js to trigger the scraping process. If the agent has shell capabilities, it may attempt to run this script. \n- [EXTERNAL_DOWNLOADS]: The skill communicates with api.apify.com, a well-known service for web scraping and automation. These interactions are consistent with the skill's primary function and the author's established presence on the platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 06:38 PM
Security Audit — agent-trust-hub — finding-instagram-creators-by-location