The Agent Skills Directory

[SAFE]: The skill provides comprehensive instructional content and LaTeX styling for scientific manuscripts. No malicious patterns such as credential harvesting, exfiltration, or unauthorized command execution were identified. External domains referenced (e.g., equator-network.org, icmje.org, and various journal publishers) are trusted scientific resources.
[COMMAND_EXECUTION]: The skill uses Bash to facilitate the compilation of LaTeX documents using standard utilities (xelatex, bibtex, latexmk). These operations are consistent with the skill's primary purpose and do not represent a security risk.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external research data, creating a potential surface for indirect prompt injection.
Ingestion points: External literature data retrieved via the alterlab-research-lookup tool mentioned in SKILL.md.
Boundary markers: The instructions do not define explicit delimiters for tool outputs, but they emphasize verification of citations.
Capability inventory: The skill uses Write and Bash to generate and compile documents.
Sanitization: No specific sanitization logic is described for external data.
Note: This surface is inherent to the skill's functional requirements and is considered safe in this context as no exploitation was observed.

alterlab-scientific-writing