case-study-writing

Fail

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • Remote Code Execution (CRITICAL): The skill instructs users to install a CLI tool using the pattern curl -fsSL https://cli.inference.sh | sh. This is a highly dangerous practice that executes unverified remote scripts directly in the system shell. The domain 'inference.sh' is not on the trusted external sources list.
  • Dynamic Execution (MEDIUM): The skill includes instructions to execute arbitrary Python code via infsh app run infsh/python-executor. While intended for generating charts, this capability allows for general-purpose code execution within the tool environment.
  • Indirect Prompt Injection (LOW): The skill ingests untrusted data from external sources via tavily/search-assistant and exa/search.
  • Ingestion points: SKILL.md uses web search tools to gather industry benchmarks and statistics.
  • Boundary markers: Absent. The data is interpolated directly into the context without delimiters or instructions to ignore embedded commands.
  • Capability inventory: The skill has access to bash-like commands (infsh) and Python execution, which could be targeted by instructions found in search results.
  • Sanitization: Absent. There is no evidence of filtering or validation of the search results before processing.
Recommendations
  • HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 18, 2026, 01:55 AM
Security Audit — agent-trust-hub — case-study-writing