content-engine

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains no executable code, remote downloads, or instructions that bypass safety protocols. Its primary function is providing guidelines for AI-driven content creation.- [DATA_INGESTION_RISK]: The skill is designed to ingest and process external sources such as articles, transcripts, and internal notes to generate social media content. This creates a surface for indirect prompt injection where malicious instructions hidden in the source material could influence the agent's output.
  • Ingestion points: Extracts content from articles, notes, memos, product demos, docs, changelogs, transcripts, and screenshots (SKILL.md).
  • Boundary markers: No specific delimiters or "ignore embedded instructions" markers are used for source material.
  • Capability inventory: Mentions the x-api skill for sourcing and publishing, which could be manipulated if the input source is adversarial.
  • Sanitization: No input validation or sanitization steps are specified for the source materials.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 12:19 AM
Security Audit — agent-trust-hub — content-engine