architect-review
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses $ARGUMENTS to ingest user input without using boundary markers (such as XML tags or triple quotes) to separate it from the system instructions. This creates a surface for indirect prompt injection, where user input could attempt to override the agent's behavior.
- Ingestion points: $ARGUMENTS in SKILL.md.
- Boundary markers: Absent. User content is interpolated directly into the instruction sentence.
- Capability inventory: No dangerous capabilities such as file system writes, network access, or shell command execution were identified in the skill content.
- Sanitization: Absent. The input is not validated or sanitized before being included in the prompt.
Audit Metadata