trends-in-cognitive-sciences
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill functions as a domain-specific instruction set for an AI agent. It consists entirely of markdown text and metadata for journal submission guidance. It does not contain any executable scripts, binaries, or automated command-line operations.
- [DATA_EXPOSURE]: The instructions reference internal resource files such as
../../resources/source-basis.md. These are relative paths pointing to the agent's own internal documentation and do not represent a risk of sensitive system file exposure, such as SSH keys or credentials. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied research data to provide feedback. While it does not include explicit boundary markers or sanitization instructions, the skill does not grant the agent any exploitable capabilities (such as network access, file system writes, or shell execution) that would make an injection attack viable.
Audit Metadata