ai-podcast-creation

Fail

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • REMOTE_CODE_EXECUTION (CRITICAL): The skill's documentation and execution flow rely on the command curl -fsSL https://cli.inference.sh | sh. This is a classic 'curl pipe to sh' pattern that executes unverified remote scripts with the user's current shell privileges. The domain inference.sh is not a trusted source according to the security policy.
  • EXTERNAL_DOWNLOADS (HIGH): The skill prompts the download of external binaries and scripts from https://cli.inference.sh and encourages adding further untrusted skills via npx skills add inference-sh/skills@....
  • COMMAND_EXECUTION (MEDIUM): The skill requests broad permission for the Bash(infsh *) tool. This allows the agent to execute any sub-command of infsh, which can interact with the local filesystem (writing .json files) and the network.
  • PROMPT_INJECTION (LOW): (Indirect Prompt Injection) The skill contains a 'NotebookLM-Style' workflow that ingests untrusted document content (<your-document-content>) and interpolates it directly into a prompt for Claude-3.5-Sonnet.
  • Ingestion points: SKILL.md (NotebookLM-Style Content section).
  • Boundary markers: Absent. The document content is placed directly after a colon in the prompt string.
  • Capability inventory: Subprocess calls (via infsh app run), file-writing (> script.json), and network operations.
  • Sanitization: None detected. This allows an attacker to embed instructions within a document that could manipulate the podcast script generation or subsequent tool calls.
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, 01:56 AM