seo-content-brief

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the infsh command-line tool to execute specialized applications for search, keyword research, and image generation on the inference.sh platform.
  • [EXTERNAL_DOWNLOADS]: Recommends the installation of additional functional modules using npx skills add from the inference-sh repository, which is standard for this ecosystem.
  • [PROMPT_INJECTION]: Exhibits an indirect prompt injection surface as it ingests and processes content from external URLs during SERP analysis.
  • Ingestion points: The tavily/extract tool (referenced in SKILL.md) reads and processes content from arbitrary competitor URLs provided in the input.
  • Boundary markers: None identified in the provided templates to distinguish between instructions and extracted content.
  • Capability inventory: Access to Bash and the infsh utility suite.
  • Sanitization: No explicit sanitization or filtering of external web content is mentioned before the agent processes it for the content brief.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 08:26 AM