skills/peter-tu-zynkr/zynkr-skill-builder/recruiter-interview-question-customize/Gen Agent Trust Hub
recruiter-interview-question-customize
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, creating a potential surface for indirect prompt injection. 1. Ingestion points: User-provided 'Resume' and 'Job description' inputs in
SKILL.mdandagents/recruiter-mock-interview.md. 2. Boundary markers: The template uses bullet points for structure, but lacks explicit boundary delimiters or instructions to ignore embedded commands. 3. Capability inventory: Analysis confirms the skill is limited to text generation and lacks high-risk capabilities like network access, file writing, or command execution. 4. Sanitization: No evidence of input validation or escaping for the external data. - [SAFE]: Documentation links target Google Docs, a well-known service, which is a safe practice for project references.
Audit Metadata