aspirational-systems-iceberg
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill takes untrusted user input (such as
desired_eventandcontext) and interpolates it directly into the prompt template without sanitization or explicit instruction to the model to ignore potential commands within that input. - Ingestion points: User-provided fields defined in
SKILL.md(desired_event,context,student_level,current_reality,stakeholders,constraints). - Boundary markers: The prompt lacks explicit delimiters (e.g., XML tags or triple quotes) around user inputs and does not include instructions to the model to ignore embedded commands.
- Capability inventory: None. The skill does not use any tools, network operations, file system access, or command execution. It only produces text output.
- Sanitization: No input validation or escaping is performed on the user-provided text.
- [NO_CODE]: The skill consists entirely of descriptive metadata and natural language prompt instructions. It does not contain any executable scripts, shell commands, or binary files.
Audit Metadata