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
WebSearchandWebFetchoperations. - 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