Skills
skills/1nfsh-s3/skills/case-study-writing/Gen Agent Trust Hub

case-study-writing

Fail

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides instructions to install a CLI tool by downloading and piping a script from https://cli.inference.sh into a shell environment.
  • [EXTERNAL_DOWNLOADS]: Fetches external resources and additional skill modules from the inference-sh organization using the npx skills add command.
  • [COMMAND_EXECUTION]: Executes system commands via the infsh utility to perform research tasks and run Python code for chart generation.
  • [PROMPT_INJECTION]: Identifies an indirect prompt injection surface where untrusted data from the web can influence agent behavior.
  • Ingestion points: Search results from tavily and exa applications are loaded into the agent's context as part of the research workflow.
  • Boundary markers: No specific delimiters or "ignore instructions" prompts are implemented for the processed external search data.
  • Capability inventory: The skill possesses the capability to run shell commands and execute Python scripts through the infsh toolset.
  • Sanitization: No evidence of sanitization or structural validation for the external search data is found.
Recommendations
  • HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 8, 2026, 02:51 AM