veadk-go-skills
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill takes user-provided functional requirements as input and uses them to generate executable code, which is then saved to the local file system.
- Ingestion points: User functional requirements and existing Enio code provided in the prompt (as described in SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the ingested user data.
- Capability inventory: The skill is explicitly designed to generate code and save it to the local file system (agent_name/agent.py).
- Sanitization: There are no explicit instructions for the agent to sanitize the generated code or validate its safety before writing it to the disk, creating a surface where user-supplied malicious logic could be persisted as executable code.
Audit Metadata