find-similar-functions

Warn

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: MEDIUMREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill recommends using bunx @rayhanadev/truffler, which downloads and executes code from a remote third-party package registry. This can be exploited if the package or the author's account is compromised.\n- [EXTERNAL_DOWNLOADS]: Execution of bunx @rayhanadev/truffler triggers a download of the package from the NPM registry at runtime.\n- [COMMAND_EXECUTION]: The skill relies on shell command execution to perform its primary tasks, using tools like bun, bunx, and the truffler binary.\n- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it reads and processes external data (source code) without proper boundaries or sanitization.\n
  • Ingestion points: Scans source code directories (e.g., src/) to identify symbols.\n
  • Boundary markers: Missing markers to distinguish between legitimate code and potentially malicious instructions embedded in comments or strings.\n
  • Capability inventory: Significant capabilities including shell command execution (bun, bunx).\n
  • Sanitization: No validation or filtering is performed on the data retrieved from the files before it is processed by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 13, 2026, 05:30 AM
Security Audit — agent-trust-hub — find-similar-functions