ea-academic-writer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed entirely of natural language instructions for text processing. It does not define or call any external scripts, binaries, or tools, and it does not perform any network or file system operations.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided academic text or notes, which creates a theoretical surface for indirect prompt injection if the input contains instructions disguised as data.
- Ingestion points: User input is accepted for paragraph critique or for expansion into academic writing as described in the skill's instructions.
- Boundary markers: The skill instructions create a strong contextual frame by requiring the agent to analyze input specifically against academic criteria and produce structured output variants.
- Capability inventory: The agent has no access to shell commands, network requests, or file system modifications within this skill context.
- Sanitization: No specific input sanitization is defined, but the agent's output is strictly limited to three defined academic variants, which mitigates the risk of executing instructions contained within the user input.
Audit Metadata