scraping-instagram-location-posts

Warn

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: MEDIUMDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill accepts a customMapFunction input parameter, which is a string containing a JavaScript function. This code is passed to the Apify platform to be executed during the data transformation phase of the scraping process, allowing for remote execution of user-supplied logic.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from Instagram posts, including captions and author handles, which are returned to the agent context.
  • Ingestion points: External data is fetched from Instagram via the Apify API (api.apify.com) in SKILL.md.
  • Boundary markers: The instructions do not define clear delimiters or "ignore instructions" wrappers for the retrieved post content.
  • Capability inventory: The skill uses local command execution (node scripts/run_actor.js) and network operations via curl.
  • Sanitization: No sanitization or escaping of the Instagram captions or metadata is specified before interpolation into the output format.
  • [EXTERNAL_DOWNLOADS]: The skill fetches data and triggers automation through the Apify REST API (api.apify.com). This is a well-known service and the primary infrastructure for the skill's stated purpose.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a local script (node scripts/run_actor.js) to interact with the Apify API and handle results. It also provides curl commands for manual fallbacks.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 2, 2026, 06:30 PM
Security Audit — agent-trust-hub — scraping-instagram-location-posts