twitter-thread-creation

Fail

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: CRITICALEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
  • [REMOTE_CODE_EXECUTION] (CRITICAL): The skill instructs the user to execute curl -fsSL https://cli.inference.sh | sh. Piping a remote script directly to a shell is a major security risk as it allows an untrusted source to execute arbitrary code on the host system without inspection.
  • [EXTERNAL_DOWNLOADS] (HIGH): The domain cli.inference.sh is not a recognized trusted source. Downloads and execution patterns from untrusted domains are treated with high severity.
  • [CREDENTIALS_UNSAFE] (HIGH): The skill guides users to perform infsh login. Because the installation method is unverified and the source is untrusted, there is a risk that this login process could capture or exfiltrate user credentials.
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The skill references several external packages via npx skills add from the inference-sh scope. These are unverifiable dependencies that further expand the attack surface.
  • [COMMAND_EXECUTION] (MEDIUM): The skill utilizes several tools with high-risk capabilities, such as infsh/agent-browser for web navigation and x/post-create for social media interaction. If the underlying infsh binary is compromised via the untrusted installation method, these tools could be used for data exfiltration or unauthorized account actions.
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, 02:01 AM