ecological-inquiry-anchor-designer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it interpolates user-provided inputs directly into a system prompt without the use of boundary markers or sanitization.
- Ingestion points: The fields
local_ecosystem,curriculum_objective,student_level,time_frame,school_grounds,community_expertise, andstudent_prior_experienceare all interpolated into the final prompt via template tags (e.g.,{{local_ecosystem}}). - Boundary markers: Absent. There are no delimiters (like XML tags, triple quotes, or specific markers) to isolate untrusted user input from the system instructions.
- Capability inventory: The skill is limited to text generation and does not utilize file-system write tools, network operations, or subprocess execution.
- Sanitization: No explicit instructions are provided to the model to ignore or escape instructions embedded within the user-provided data.
Audit Metadata