jobs-interview

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches installation scripts for the sjctl CLI tool from the vendor's official GitHub repository (solid-company/solid-jobs-skills).
  • [REMOTE_CODE_EXECUTION]: Provides instructions to download and execute shell scripts via curl piped to bash (macOS/Linux) and Invoke-RestMethod piped to Invoke-Expression (Windows). These resources are hosted on a well-known service (GitHub) under the skill author's organization (solid-company).
  • [COMMAND_EXECUTION]: Executes the sjctl CLI tool to manage job offers, user profiles, and interview preparation data stored in the local cache.
  • [PROMPT_INJECTION]: The skill ingests untrusted job offer descriptions which could potentially contain indirect instructions.
  • Ingestion point: sjctl offer show in SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: Subprocess calls to sjctl in SKILL.md.
  • Sanitization: Absent. This constitutes a surface for indirect prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 08:13 AM
Security Audit — agent-trust-hub — jobs-interview