salary-research

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches compensation data from well-known career services including Levels.fyi, Glassdoor, and Team Blind to provide current market data.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from the web, which creates a surface for indirect prompt injection.
  • Ingestion points: Results from WebSearch and WebFetch operations.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded instructions in the fetched content.
  • Capability inventory: The skill has access to shell execution (Bash) and file modification (Write, Edit) tools.
  • Sanitization: No explicit sanitization or filtering of external content is performed before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 05:36 AM
Security Audit — agent-trust-hub — salary-research