The Agent Skills Directory

[SAFE]: The skill adheres to its stated purpose of providing an academic evaluation framework. No malicious patterns were identified in the instructions, scripts, or reference materials.
[COMMAND_EXECUTION]: The included Python script scripts/calculate_scores.py is a utility for processing evaluation scores. It uses standard libraries for JSON parsing and file output, posing no security risk in its implementation.
[DATA_EXFILTRATION]: There are no indicators of data exfiltration. The skill does not perform network requests or access sensitive system credentials.
[PROMPT_INJECTION]: The skill includes a surface for indirect prompt injection as it processes user-provided scholarly documents. However, this is inherent to the skill's function and lacks high-risk capabilities that would enable an attack. The ingestion points include research papers and proposals described in the evaluation workflow (SKILL.md), there are no explicit boundary markers or sanitization routines defined, and the primary capability is generating a score report to disk. This configuration is assessed as safe within the intended use-case.

scholar-evaluation