apify-trend-analysis

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the execution of shell commands using the mcpc CLI and a local Node.js script (run_actor.js) to interact with the Apify platform.
  • [DATA_EXFILTRATION]: The script communicates with https://api.apify.com to manage actor runs and download dataset results. This interaction targets a well-known service and is necessary for the skill's primary functionality.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes and displays content from untrusted external sources like Instagram, TikTok, and YouTube.
  • Ingestion points: Data is ingested in run_actor.js via the displayQuickAnswer function, which fetches dataset items from Apify.
  • Boundary markers: The skill does not use specific delimiters or instructions to ignore potential commands embedded in the retrieved social media data.
  • Capability inventory: The skill uses command-line execution for the mcpc tool and the node runner script.
  • Sanitization: Content is truncated for length before display, but no validation or filtering is performed to identify or neutralize embedded instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 07:27 AM