goal-setting-protocol-designer
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely declarative and does not include any scripts, executable files, or tool definitions. No malicious patterns such as obfuscation, credential harvesting, or persistence mechanisms were found.- [PROMPT_INJECTION]: The skill uses template interpolation for user-provided data, creating a surface for indirect prompt injection.
- Ingestion points: Inputs such as {{learning_context}} and {{student_profiles}} are directly inserted into the prompt in SKILL.md.
- Boundary markers: Absent; user input is not delimited by markers like XML tags or triple quotes.
- Capability inventory: None; the skill does not define any tools, shell commands, or network capabilities.
- Sanitization: None; input is interpolated as raw text. Due to the total lack of execution capabilities or access to sensitive data, this surface presents no practical security risk and is classified as safe.
Audit Metadata