service-learning-project-designer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates untrusted user data into the model prompt without using boundary markers or sanitization, creating a surface for prompt injection.
- Ingestion points: User-provided fields such as
community_needandcurriculum_connectionare interpolated directly into the prompt template inSKILL.md. - Boundary markers: The skill does not use delimiters (like XML tags, triple backticks, or specific guardrail instructions) to isolate user input from the core instructions.
- Capability inventory: Analysis confirms the skill lacks any capabilities for network operations, file system modification, or command execution, which significantly limits the impact of any potential injection.
- Sanitization: There is no evidence of input filtering or escaping to prevent users from attempting to override the agent's persona or instructions.
Audit Metadata