capacitor-security

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes bunx to download and run the capsec package. This is the intended delivery method for the vendor's security tool and is considered safe within the vendor's context.\n- [COMMAND_EXECUTION]: The skill enables the execution of CLI commands to scan the local filesystem for security issues.\n- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection through the processing of untrusted project data.\n
  • Ingestion points: Project source files and configuration data (SKILL.md).\n
  • Boundary markers: Absent.\n
  • Capability inventory: File system access and CLI command execution (SKILL.md).\n
  • Sanitization: Not present in the documented workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 10:53 AM