social-amplification

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external pillar assets (articles, studies) and local knowledge bases (Obsidian vaults). This creates an attack surface where untrusted data could influence agent behavior.
  • Ingestion points: Accesses external pillar assets and local markdown files.
  • Boundary markers: No explicit delimiters or instructions to ignore instructions within ingested data are provided.
  • Capability inventory: The skill is capable of reading and writing to the local file system (appending to SEO logs) and generating content for social platforms.
  • Sanitization: There is no evidence of sanitization or validation for external content.
  • [EXTERNAL_DOWNLOADS]: The skill references several external resources for SEO strategy and metrics.
  • Evidence: Links to industry research and blog posts on ahrefs.com, semrush.com, and tryprofound.com, as well as academic research on arxiv.org.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 06:28 AM