Skills
skills/lisbeth718/pseo-skills/pseo-schema/Gen Agent Trust Hub

pseo-schema

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill defines functions to process page data into JSON-LD scripts, creating a potential path for data-driven injection. 1. Ingestion points: Page data and FAQ arrays in generateArticleSchema and generateFAQSchema within SKILL.md. 2. Boundary markers: None present to isolate data from schema logic. 3. Capability inventory: Access to Bash, Edit, Write, Grep, Glob, and Read tools. 4. Sanitization: The logic uses JSON.stringify for serialization but lacks explicit sanitization or validation of the input source data.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:40 PM