job-hunter

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources such as job posting URLs and web search results (e.g., Glassdoor reviews) to generate resumes, cover letters, and interview prep. This creates a surface for indirect prompt injection where a malicious job posting could attempt to influence the agent's behavior.
  • Ingestion points: Processes content from user-provided job posting URLs and automated web searches for company reviews.
  • Boundary markers: No explicit instructions are provided to the agent to treat external job posting content as untrusted or to use delimiters to isolate it.
  • Capability inventory: The skill has the capability to write and modify local markdown and JSON files (resume.md, cover-letter-[company].md, ~/.openclaw/job-tracker.json).
  • Sanitization: There is no mention of sanitizing or validating the content retrieved from external URLs before processing it into documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 09:54 AM
Security Audit — agent-trust-hub — job-hunter