talking-head-production

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION] (CRITICAL): The command curl -fsSL https://cli.inference.sh | sh is present in the Quick Start section. This pattern downloads and executes code from an untrusted remote source without verification, allowing for arbitrary code execution on the host machine.\n- [EXTERNAL_DOWNLOADS] (HIGH): The skill downloads and installs dependencies from https://cli.inference.sh and inferencesh/skills via npx. Neither the domain nor the organization are included in the trusted external sources whitelist.\n- [COMMAND_EXECUTION] (MEDIUM): The skill frontmatter specifies allowed-tools: Bash(infsh *), which grants the agent broad permissions to execute any subcommand of the infsh CLI tool. This increases the risk of exploitation if the tool contains vulnerabilities or processes malicious inputs.\n- [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection. Untrusted data enters the agent context via the --input parameters in infsh tool calls (found in SKILL.md). There are no boundary markers or sanitization logic present to prevent embedded instructions in user-provided prompts from influencing agent behavior during execution.
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 17, 2026, 06:43 PM