upwork-job-qualifier

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted external content as a core function.
  • Ingestion points: Untrusted data enters the agent context via user-pasted Upwork job descriptions and "About the client" history panels.
  • Boundary markers: The instructions lack explicit boundary markers or delimiters to distinguish between data being analyzed and the instructions themselves.
  • Capability inventory: The skill is designed to read local files (specifically upwork-profile.md or ~/.claude/upwork-profile.md) to personalize its advice. It does not possess capabilities for network operations, command execution, or file writing.
  • Sanitization: There are no mechanisms for sanitizing, escaping, or validating the external content to prevent it from influencing agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 04:17 PM
Security Audit — agent-trust-hub — upwork-job-qualifier