jobs-create-profile

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides installation instructions for the sjctl CLI tool by downloading and executing shell scripts directly from the vendor's GitHub repository.
  • Evidence:
  • macOS/Linux: curl -fsSL https://raw.githubusercontent.com/solid-company/solid-jobs-skills/v0.5.0/scripts/install-sjctl.sh | bash
  • Windows: irm https://raw.githubusercontent.com/solid-company/solid-jobs-skills/v0.5.0/scripts/install-sjctl.ps1 | iex
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands using the sjctl binary to perform database operations (add, import, list, show, set-default).
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of natural language self-descriptions or pasted CV text provided by the user.
  • Ingestion points: natural language input and CV text in SKILL.md.
  • Boundary markers: None specified for the interpolation of user data into the processing logic.
  • Capability inventory: The skill uses sjctl for database writes and reads, and writes temporary files to the filesystem.
  • Sanitization: No explicit sanitization or validation of the input text is mentioned before it is processed by the agent to fill markdown templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 08:13 AM
Security Audit — agent-trust-hub — jobs-create-profile