glassdoor-salary-data

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the scavio package from standard registries (PyPI and NPM). These packages are vendor-provided resources used to facilitate communication with the scavio-ai API.
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches and processes employee reviews and company descriptions from Glassdoor, which are external and potentially user-influenced content.
  • Ingestion points: Data is retrieved from the /api/v1/glassdoor/company and /api/v1/glassdoor/reviews endpoints.
  • Boundary markers: The skill does not explicitly define delimiters or instructions for the agent to distinguish between its primary instructions and the fetched review content.
  • Capability inventory: The skill uses the requests library to fetch data but does not perform sensitive file operations, shell command execution, or other high-risk actions based on the API response.
  • Sanitization: The skill documentation does not mention specific sanitization or filtering of the external data before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 12:23 PM
Security Audit — agent-trust-hub — glassdoor-salary-data