zynkr-recruiter

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, specifically candidate resumes and interview transcripts, which are passed to sub-agents for evaluation and decision support. This ingestion creates a vulnerability to indirect prompt injection attacks where malicious content hidden in a resume could attempt to manipulate the agent's output.\n
  • Ingestion points: User-provided candidate resumes (text or ZIP files) in recruiter-resume-screener.md and interview transcripts in recruiter-calibrator.md.\n
  • Boundary markers: The prompt instructions lack explicit delimiters or warnings to ignore commands embedded within the candidate data.\n
  • Capability inventory: The system generates hiring recommendations and summaries based on these inputs.\n
  • Sanitization: There is no evidence of pre-processing or sanitization of the external text content.\n- [EXTERNAL_DOWNLOADS]: The installation instructions in SKILL.md reference a remote resource at https://github.com/peter-tu-zynkr/zynkr-skill-builder. This command fetches additional skill components from the author's repository during setup.\n- [COMMAND_EXECUTION]: The documentation provides a bash setup command (npx skills add ...) for the user to initialize the skill, which executes a package manager to fetch remote components.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 07:31 PM
Security Audit — agent-trust-hub — zynkr-recruiter