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.mdor~/.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