Skills
skills/inference-skills/skills/prompt-engineering/Gen Agent Trust Hub

prompt-engineering

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the belt CLI tool (belt login, belt app run) to interact with AI models. This is the intended functionality of the skill for the inference.sh platform.
  • [EXTERNAL_DOWNLOADS]: The skill references an installation guide hosted on the vendor's GitHub repository (raw.githubusercontent.com/inference-sh/skills/...). This is a legitimate resource for setting up the required CLI tool.
  • [PROMPT_INJECTION]: The provided templates for code review and content writing use placeholders like [code] and [article text]. These represent ingestion points where an agent might process untrusted external data. Ingestion points: SKILL.md (placeholders in templates); Boundary markers: Absent; Capability inventory: Bash(belt *) in SKILL.md; Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 08:02 PM
Security Audit — agent-trust-hub — prompt-engineering