bahasa-seo

Pass

Audited by Gen Agent Trust Hub on Oct 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to analyze external, user-generated content to identify 'audience diction,' which constitutes an ingestion surface for untrusted data.
  • Ingestion points: The agent is instructed in references/riset-kata-kunci.md to review competitor product ulasan (reviews) on marketplaces and Google Maps, as well as social media comment sections.
  • Boundary markers: There are no explicit instructions to use delimiters or safety wrappers when processing these external text samples to prevent the agent from following instructions embedded within the data.
  • Capability inventory: The skill is primarily a content generation guide and does not define tools for file system modification, network exfiltration, or command execution.
  • Sanitization: No sanitization or filtering logic is specified for the external comments and reviews prior to processing.
  • [EXTERNAL_DOWNLOADS]: The skill mentions and utilizes established SEO research tools and data sources for content validation.
  • Evidence: References to Google Autocomplete, Ahrefs, Semrush, and Ubersuggest are included as standard resources for verifying keyword volume and search intent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 10, 2026, 12:08 PM