linkedin-influencer-discovery

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves data from the Apify platform's official API (api.apify.com). This is a well-known service, and the data fetched is essential for discovering LinkedIn influencers as intended by the skill's design.- [CREDENTIALS_UNSAFE]: The skill requires an APIY_API_TOKEN. The script scripts/discover_influencers.py handles this token by accepting it via environment variables or command-line arguments and passing it as a query parameter in HTTP requests to Apify.- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks due to its data ingestion model.
  • Ingestion points: Influencer biographies and names are fetched from the Apify powerai/influencer-filter-api-scraper actor.
  • Boundary markers: The output does not include clear boundary markers or instructions for the agent to ignore potentially malicious content within the influencer bios.
  • Capability inventory: The skill uses network access to call the Apify API but does not have capabilities for file system modification or arbitrary shell command execution.
  • Sanitization: The script does not perform sanitization or filtering of the content retrieved from influencer profiles before presenting it to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 06:02 PM