content-repurposing

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 explicitly instructs the execution of curl -fsSL https://cli.inference.sh | sh. This is a confirmed remote code execution pattern that pipes unverified content from a non-trusted domain directly into a shell interpreter.
  • External Downloads (MEDIUM): The skill attempts to install multiple external packages using npx skills add inference-sh/skills@.... Since inference-sh is not a trusted organization, these dependencies are unverifiable and could contain malicious code.
  • Indirect Prompt Injection (LOW): The skill is designed to ingest and process untrusted data (blog posts, transcripts) and utilize it in downstream tasks like social media posting.
  • Ingestion points: Processes external blog content and audio transcriptions via infsh apps.
  • Boundary markers: Absent; there are no delimiters or instructions to prevent the agent from obeying instructions embedded in the content being repurposed.
  • Capability inventory: The skill has access to Bash(infsh *), which allows for network-connected actions like posting to X/Twitter (x/post-create) and generating media.
  • Sanitization: Absent; the skill does not show any signs of escaping or validating the input data before passing it to generative tools.
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, 01:18 AM