apify-influencer-discovery-v2

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and summarizes untrusted data scraped from social media platforms (e.g., profile bios, comments, and post descriptions). Malicious instructions hidden in this data could potentially influence the agent's summarization or subsequent actions.
  • Ingestion points: Social media profile data and metrics summarized in Step 5 of the workflow.
  • Boundary markers: The skill lacks explicit delimiters or warnings to the agent to ignore instructions embedded within the scraped content.
  • Capability inventory: The skill possesses file-write capabilities through run_actor.js and command execution via mcpc and node scripts.
  • Sanitization: While the run_actor.js script truncates long fields, it does not perform semantic sanitization or filtering of the ingested content.
  • [COMMAND_EXECUTION]: The workflow relies on shell commands to interact with the Apify platform and run local helper scripts, including logic to extract environment variables from local configuration files.
  • [EXTERNAL_DOWNLOADS]: The skill performs network requests to api.apify.com and mcp.apify.com to facilitate data extraction and actor management through the official endpoints of the Apify platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 07:59 AM
Security Audit — agent-trust-hub — apify-influencer-discovery-v2