The Agent Skills Directory

[SAFE]: The skill focuses exclusively on academic research workflows, including SLR (Systematic Literature Review) and PRISMA methodologies. No instructions attempting to bypass safety filters or override agent behavior were detected.
[NO_CODE]: The skill is composed entirely of markdown instructions and YAML configuration. It does not include any scripts (Python, Node.js, Shell) or binary executables, significantly reducing the potential for malicious behavior.
[SAFE]: References to external academic repositories such as Google Scholar, Web of Science, Scopus, and the National Digital Library of Theses and Dissertations in Taiwan (ndltd.ncl.edu.tw) target well-known and trusted scholarly services.
[SAFE]: The integration with Notion for literature card management is a documented feature intended for data organization. Usage of this well-known service is consistent with the skill's stated purpose of literature review management.
[PROMPT_INJECTION]: Indirect injection surface analysis:
Ingestion points: External content retrieved from academic databases via WebSearch (SKILL.md).
Boundary markers: Absent.
Capability inventory: Access to Notion, Write, and Bash tools (frontmatter).
Sanitization: Absent.
Conclusion: While the skill processes untrusted web data, the risk is negligible as it targets peer-reviewed academic sources and does not contain automated scripts that exploit its tool access.

tw-research-lit-review