project-brief-designer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided inputs such as project topics and student profiles by inserting them directly into the system prompt. This creates a surface for indirect prompt injection where malicious text in the input could attempt to redirect the AI's behavior. However, the skill has no access to sensitive tools, the network, or the file system, which restricts the impact to the generated text content.
- Ingestion points: Multiple input variables are interpolated into the instructions in SKILL.md.
- Boundary markers: While bold headers label the inputs, there are no specific delimiters or instructions to ignore embedded commands within the data.
- Capability inventory: The skill is a text-generation tool and does not include any capabilities for command execution, file writing, or network communication.
- Sanitization: No sanitization or validation of the input text is performed.
Audit Metadata