odev-ai
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes technical and functional specifications to populate Odoo records via MCP tools, creating an attack surface where malicious instructions embedded in the specifications could influence agent behavior.
- Ingestion points: Technical analysis or functional specification documents (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or boundary markers to isolate the untrusted specification text from the agent's core instructions.
- Capability inventory: The skill utilizes MCP tools to write to various Odoo models, including business logic, database fields, and migration scripts (SKILL.md).
- Sanitization: No sanitization or validation logic is defined to filter potentially malicious instructions within the specifications before they are processed by the agent.
Audit Metadata