linkedin-scraper-api

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, specifically LinkedIn member profiles, posts, and comments.
  • Ingestion points: Untrusted data enters the agent context through API responses from api.scavio.dev containing user-generated LinkedIn content (e.g., about sections, text in posts, and comment threads).
  • Boundary markers: The skill returns data as structured JSON, which provides a natural boundary between data fields and the agent's instructions.
  • Capability inventory: The skill utilizes the requests library and the scavio SDK to perform HTTP POST requests to the vendor's API.
  • Sanitization: There is no explicit sanitization logic for the string content returned from LinkedIn; however, this is standard for data retrieval tools where the agent is expected to handle the content as data.
  • [EXTERNAL_DOWNLOADS]: The skill documentation references the installation of the vendor's official SDK.
  • Evidence: Recommends installing scavio==0.15.0 via pip to facilitate interaction with the API.
  • [COMMAND_EXECUTION]: The skill provides examples of configuring environment variables for authentication.
  • Evidence: Instructs the user to export SCAVIO_API_KEY=sk_live_your_key for secure credential management.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 12:23 PM
Security Audit — agent-trust-hub — linkedin-scraper-api