seo-content-brief
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection through the processing of untrusted external data.
- Ingestion points: The skill uses the
infsh app run tavily/extractcommand to fetch and process content from external URLs in SKILL.md. - Boundary markers: No delimiters or protective instructions are provided to prevent the agent from following commands embedded in the external content.
- Capability inventory: The skill utilizes the
infshCLI for searching, extraction, and generating images via the Bash tool. - Sanitization: No content sanitization or validation steps are defined for the extracted data.
- [COMMAND_EXECUTION]: The skill uses the
infsh(inference.sh) CLI to execute various search and research applications. These tools are provided by the skill's author, inference-shell, and are used to interact with search engines and content extraction services. - [EXTERNAL_DOWNLOADS]: The documentation suggests fetching additional skills from the
inference-shorganization usingnpx skills add, which facilitates the download of external code to extend the agent's capabilities.
Audit Metadata