case-study-writing

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions for the belt CLI hosted on the vendor's GitHub repository at https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md.- [COMMAND_EXECUTION]: The skill executes various commands using the belt CLI via the Bash tool, including account authentication, industry research using search assistants, and running data visualization applications.- [DYNAMIC_EXECUTION]: The skill includes a static Python template that is executed at runtime via the infsh/python-executor to generate before-and-after comparison charts.- [INDIRECT_PROMPT_INJECTION]: The skill processes external customer data such as quotes and metrics to generate case studies. While the skill lacks explicit boundary markers or sanitization for this ingested data, the capabilities utilized (search and charting) are necessary for the skill's stated purpose of research-driven writing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 08:29 PM
Security Audit — agent-trust-hub — case-study-writing