jotbird-publish

Fail

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: HIGHCREDENTIALS_UNSAFECOMMAND_EXECUTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill file contains a hardcoded authentication token (jb_c57e765852df55f32daa0f8c745b3241552a052ddfbe1907f73a4d67d107fe4b) assigned to the JOTBIRD_API_KEY environment variable. Hardcoding secrets in skill instructions is a dangerous practice that can lead to credential theft or unauthorized service usage.
  • [COMMAND_EXECUTION]: The skill makes extensive use of the curl command-line tool to perform network operations, including sending user-provided content to external endpoints (jotbird.com).
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface where it ingests untrusted Markdown content from users and transmits it to a remote API. While this is the intended functionality, the lack of explicit sanitization or boundary markers for the interpolated content presents a potential path for indirect injection attacks if the downstream service or agent processes the content further.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Aug 14, 2026, 01:42 PM
Security Audit — agent-trust-hub — jotbird-publish