context-mode

Warn

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires a global installation of 'context-mode' from npm, which is a third-party dependency from an unverified author.
  • [COMMAND_EXECUTION]: Tools such as 'ctx_execute' and 'ctx_execute_file' allow the agent to run arbitrary shell commands on the system.
  • [DATA_EXFILTRATION]: The 'ctx_fetch_and_index' tool allows the agent to make arbitrary HTTP requests, which can be leveraged for data exfiltration.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from external URLs (ingestion point: ctx_fetch_and_index) without sanitization or boundary markers, and provides high-privilege tools like 'ctx_execute' that could be triggered by malicious instructions in that data.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 8, 2026, 02:29 PM
Security Audit — agent-trust-hub — context-mode