ad-script-skill

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security concerns were identified. The skill's instructions are focused entirely on text generation tasks for marketing purposes. There are no commands for file access, network requests, or credential handling.
  • [PROMPT_INJECTION]: The skill accepts user-provided information, such as product descriptions and URLs, which represents a potential surface for indirect prompt injection.
  • Ingestion points: Input fields defined in the Inputs section of SKILL.md.
  • Boundary markers: Absent; the instructions do not include specific delimiters or instructions to ignore embedded commands in the processed data.
  • Capability inventory: None; the skill is restricted to generating descriptive text and lacks any capabilities for subprocess execution, file system access, or network communication.
  • Sanitization: None; the skill relies on the AI agent's internal safety guardrails for handling input content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 04:24 PM