input-resume-explorer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted resume documents which could contain malicious instructions. The skill proactively addresses this risk by instructing the agent to treat document text as untrusted evidence and to never follow instructions embedded in it.
- [SAFE]: No suspicious patterns such as remote code execution, unauthorized network access, or credential theft were found in the provided files. The skill follows secure design principles by separating session data and enforcing boundaries on external searches.
Audit Metadata