odoo-19

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted project data, creating a potential surface for indirect prompt injection.
  • Ingestion points: The skill defines glob patterns for all primary Odoo development files including **/*.{py,xml,csv,js,ts,css,scss}.
  • Boundary markers: There are no explicit instructions or delimiters defined to distinguish between the skill's reference content and the code it analyzes.
  • Capability inventory: The skill provides the agent with patterns for database operations (ORM), file system modifications (creating/updating modules), and network/HTTP controller definition.
  • Sanitization: The skill provides excellent remediation guidance via the odoo-19-security-guide.md file, which specifically teaches the agent and developer how to prevent SQL injection, XSS, and unsafe code evaluation.
  • [EXTERNAL_DOWNLOADS]: The skill references external resources for installation and official documentation.
  • Evidence: Installation instructions in AGENTS.md point to the vendor's GitHub repository via npx skills add unclecatvn/agent-skills.
  • Evidence: SKILL.md contains multiple references to official Odoo 19 documentation hosted on GitHub.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 08:40 AM