endor-policy

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads and runs the endorctl package from the NPM registry using npx at runtime.\n- [COMMAND_EXECUTION]: Executes shell commands via npx to interact with the Endor Labs API for creating and listing security policies.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to the way it handles external input.\n
  • Ingestion points: Processes user-provided data for policy names, descriptions, filters, and exception justifications in SKILL.md.\n
  • Boundary markers: Lacks explicit delimiters or instructions to prevent the execution of malicious instructions embedded within interpolated variables.\n
  • Capability inventory: Has the capability to execute shell commands and modify organizational security settings.\n
  • Sanitization: There is no evidence of sanitization or escaping of user input before it is used in shell command arguments or JSON payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 04:26 AM