job-hunt-analyzer

Warn

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command md5 -q <work_dir>/.work/resume.md. Directly interpolating the <work_dir> variable into a shell command without validation presents a command injection risk, as a path containing shell metacharacters could execute arbitrary code.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content from resumes and job descriptions while having access to shell commands and the file system.
  • Ingestion points: Content is read from <work_dir>/.work/resume.md and various files within the <work_dir>/.work/jd-pool/ directory.
  • Boundary markers: The instructions lack explicit delimiters or warnings to the agent to ignore any instructions embedded within the processed data.
  • Capability inventory: The agent is authorized to execute shell commands (md5) and perform file system operations (read/write).
  • Sanitization: There is no evidence of content sanitization or validation before the data is used in the matching and scoring process.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 15, 2026, 10:43 AM
Security Audit — agent-trust-hub — job-hunt-analyzer