better-result-adopt
Fail
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: HIGHPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (HIGH): The skill is vulnerable to Indirect Prompt Injection (Category 8) because it processes untrusted content and possesses write capabilities.
- Ingestion points:
SKILL.md(Workflow step 2: 'Audit') directs the agent to analyze target modules in the user's codebase. - Boundary markers: Absent. There are no instructions to delimit the user code or warn the agent against following embedded instructions.
- Capability inventory:
SKILL.md(Workflow steps 6-7) requires the agent to update function signatures and callers, implying a file-write capability across the repository. - Sanitization: Absent. No filtering or validation of the analyzed source code is performed to detect or strip potential injection attacks.
Recommendations
- AI detected serious security threats
Audit Metadata