skills/smixs/seo-blog/blog-geo/Gen Agent Trust Hub

blog-geo

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external content (blog posts) retrieved via the Read and WebFetch tools. This creates an attack surface for indirect prompt injection where instructions embedded within the analyzed content could potentially influence the agent's behavior.
  • Ingestion points: Blog content, heading structures, and schema markup extracted during the audit process.
  • Boundary markers: The skill does not explicitly instruct the agent to use delimiters or specific ignore-instructions when processing the external content.
  • Capability inventory: The skill uses standard tools including Read, Write, Grep, Glob, and WebFetch for its audit tasks.
  • Sanitization: No specific filtering or sanitization of the external blog data is required before the agent processes it to generate reports and citation capsules.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 05:57 PM
Security Audit — agent-trust-hub — blog-geo