outdoor-learning-sequence-designer
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. It interpolates untrusted user inputs directly into the system prompt without sanitization or boundary markers, which could allow an attacker to manipulate the agent's behavior through crafted input.
- Ingestion points: Variables
{{learning_objective}},{{outdoor_space}}, and optional context fields inSKILL.md. - Boundary markers: Absent. The user input is placed directly after labels in the prompt text.
- Capability inventory: The skill only performs text generation and does not have access to file system tools, network operations, or shell execution.
- Sanitization: None detected in the prompt instructions.
Audit Metadata