medusa-security

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the medusa-security package via pip. This package is the core engine for the skill and is documented as a vendor resource for its primary functionality.
  • [COMMAND_EXECUTION]: The skill invokes the Medusa CLI tool using spawnSync with shell: false in scripts/cli-wrapper.cjs. This implementation follows security best practices by preventing shell injection through the use of direct argument passing.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data (source code and configuration files) during security scans, which could contain malicious patterns targeting the scanner or the agent's interpretation of results.
  • Ingestion points: Scan results are parsed by scripts/sarif-parser.cjs and scripts/json-parser.cjs from the output of the Medusa CLI.
  • Boundary markers: Findings are formatted into structured markdown reports with specific sections and tables to separate tool output from instructions.
  • Capability inventory: The skill possesses the capability to execute the Medusa scanner and write reports to the .claude/context/reports/ directory.
  • Sanitization: The skill performs basic sanitization by escaping pipe characters in findings to ensure the integrity of the generated markdown reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 06:57 PM