skills/jackjin1997/clawforge/getajob/Gen Agent Trust Hub

getajob

Warn

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (MEDIUM): The skill ingests untrusted data from web search results to generate resumes and cover letters.
  • Ingestion points: External job listings and company news retrieved via web search are processed and summarized.
  • Boundary markers: Absent. There are no instructions to delimit or treat external web content as untrusted data within the prompts.
  • Capability inventory: File system write access to ~/getajob/ and web search capabilities.
  • Sanitization: Absent. The skill does not specify any sanitization, filtering, or validation of the content retrieved from external job boards.
  • Category 2 (LOW): Data Exposure. The skill stores user preferences and application materials in a predictable local directory (~/getajob/). While this is functional for the skill's purpose, it aggregates sensitive career data that could be targeted by other malicious tools in the environment.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 08:26 AM