seo-content-brief

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Employs the infsh CLI to perform search queries, extract content, and generate visual comparison tables via HTML-to-image conversion.
  • [EXTERNAL_DOWNLOADS]: Interacts with well-known search services, specifically Tavily and Exa, to retrieve real-time search engine data and competitor content.
  • [PROMPT_INJECTION]: Identifies an indirect prompt injection surface as the skill processes and analyzes untrusted content extracted from third-party websites.
  • Ingestion points: Data is ingested through content extraction tools like tavily/extract and search results from exa/search (SKILL.md).
  • Boundary markers: The provided templates do not currently implement specific delimiters or instructions to ignore embedded commands in the processed data.
  • Capability inventory: The skill uses the Bash tool to interact with CLI-based applications and search tools (SKILL.md).
  • Sanitization: There are no explicit content sanitization or validation steps documented for the data retrieved from external URLs.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 01:40 AM