brief-glassdoor-signal

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's operations, including fetching data from Glassdoor and writing to a local working folder, align with its stated purpose of sentiment research. The use of bash tools is restricted to directory management and testing.
  • [PROMPT_INJECTION]: Potential for indirect prompt injection exists because the skill processes untrusted data from external websites. This is a low-risk surface common to research-oriented skills.
  • Ingestion points: Data fetched from Glassdoor, Levels.fyi, and Blind via WebFetch in Step 3.
  • Boundary markers: None defined for the interpolation of external reviews into the analysis process.
  • Capability inventory: The skill utilizes Write, Bash(mkdir), and Bash(test) tools to manage and store reports.
  • Sanitization: Not explicitly specified; the skill instructions favor verbatim quoting of source material.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 05:16 AM
Security Audit — agent-trust-hub — brief-glassdoor-signal