education-grant-writer
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided research descriptions to generate structured grant proposals.
- Ingestion points: User inputs for research topics, goals, and methodology are collected in Workflow Step 2.
- Boundary markers: The skill does not implement specific delimiters or 'ignore embedded instructions' warnings for the research content provided by the user.
- Capability inventory: The skill is limited to text generation and routing to other internal analytical skills for data visualization and paper searching; no shell or network execution capabilities were identified in the skill logic.
- Sanitization: No sanitization or input validation logic is present to filter malicious instructions within the user-provided research summaries.
Audit Metadata