keep-it-simple
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTION
Full Analysis
- Prompt Injection (HIGH): This skill presents a high-risk vulnerability surface for indirect prompt injection. \n- Ingestion points: User-provided feature requests and coding prompts (e.g., 'Add a way to send notification emails'). \n- Boundary markers: Absent; there are no clear delimiters or instructions to the agent to ignore instructions embedded within the user data. \n- Capability inventory: The skill is granted 'file:read' and 'file:edit' permissions in the metadata. \n- Sanitization: Absent; the skill lacks validation or filtering for the content it processes. \n- Conclusion: According to the security analysis framework, skills that process external content while possessing write or edit capabilities are tiered as HIGH risk regardless of their functional purpose.
Recommendations
- AI detected serious security threats
Audit Metadata