The Agent Skills Directory

[SAFE]: The skill is designed for report generation and research documentation. No evidence of prompt injection, data exfiltration, or malicious intent was found.
[DATA_EXPOSURE_AND_EXFILTRATION]: No sensitive file access or network operations were identified. File operations are restricted to project-local paths (e.g., Results/Reports/, Experiments/) typical of research workflows.
[INDIRECT_PROMPT_INJECTION]: The skill processes external analysis artifacts (markdown files and figure data). While this represents a data ingestion surface, the skill's primary capability is writing markdown reports to a local directory or Obsidian vault, which is consistent with its stated purpose. Risk is considered negligible for this use case.
[DYNAMIC_CONTEXT_INJECTION]: No use of shell-execution placeholders (!command) was detected in the skill configuration.

results-report