Resume Critic

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting and analyzing content from untrusted external sources, which creates a vulnerability surface for indirect prompt injection. Maliciously crafted data in a resume or repository could potentially influence the agent's evaluation logic.
  • Ingestion points: Resume content, Engineering Evidence Database, GitHub source code, and Job Description (JD) Intelligence Briefings.
  • Boundary markers: The instructions lack specific delimiters or instructions to prevent the agent from executing instructions potentially hidden within the resume or evidence data.
  • Capability inventory: The skill governs the pipeline flow, determining whether the agent proceeds to final PDF generation or returns to previous steps for targeted rewrites.
  • Sanitization: No explicit sanitization or input validation steps are described for the data processed during the audit phase.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 07:31 AM
Security Audit — agent-trust-hub — Resume Critic