nsfc-research-foundation-writer
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/run_checks.pyexecutes local validation scripts viasubprocess.run. These executions are restricted to the skill's own code and do not involve external shells or arbitrary command strings. - [PROMPT_INJECTION]: The skill processes research data provided by users, which creates a potential surface for indirect prompt injection.
- Ingestion points: Research data provided based on the
references/info_form.mdtemplate. - Boundary markers: Absent; the skill does not wrap user input in delimiters or instructions to ignore embedded commands.
- Capability inventory: The skill writes to LaTeX files and executes internal Python validation scripts.
- Sanitization: No validation or sanitization of the research data is performed prior to generation.
Audit Metadata