scientific-writing
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides legitimate instructions for academic writing and citation management according to standard guidelines such as IMRAD, APA, and AMA. The suggestion to use the author's external platform (www.k-dense.ai) is presented transparently and is consistent with the skill's stated purpose.
- [COMMAND_EXECUTION]: The skill instructs the agent to use the Bash tool to execute local Python scripts (scripts/generate_schematic.py and scripts/generate_image.py) and LaTeX (xelatex) for scientific visualization and professional report compilation.
- [PROMPT_INJECTION]: The skill incorporates external research data into its writing process, presenting an indirect prompt injection surface. Ingestion points: Data retrieved via the research-lookup skill referenced in the instructions. Boundary markers: The instructions do not define delimiters for isolating untrusted data from system prompts. Capability inventory: Bash, Write, Edit, and Read tools. Sanitization: No explicit instructions for escaping or validating external content are provided.
Audit Metadata