ea-academic-writer
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown content and contains no executable code, script references, or external dependencies.
- [PROMPT_INJECTION]: While the skill uses strong directives such as 'non-negotiable' and 'BEFORE WRITING ANYTHING', these are used to define the agent's persona and procedural methodology for academic writing. They do not attempt to bypass safety guidelines or override the system prompt in a malicious manner.
- [DATA_EXFILTRATION]: There are no indicators of network activity, credential access, or sensitive file manipulation. The skill operates solely on text provided within the chat context.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text for critique and revision. This creates a surface for indirect injection; however, the agent is strictly instructed to evaluate this text against specific academic criteria. Since the skill lacks the ability to execute code or perform network operations, the impact of such an injection is restricted to the generated text output.
- [REMOTE_CODE_EXECUTION]: No package managers, shell commands, or remote script fetching patterns are present in the documentation.
Audit Metadata