Skills
Navigate
skills/huangwb8/chineseresearchlatex/nsfc-research-foundation-writer/Gen Agent Trust Hub

nsfc-research-foundation-writer

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/run_checks.py uses subprocess.run to execute internal validation scripts (validate_skill.py and check_project_outputs.py). These calls are used to verify the skill's integrity and the consistency of project outputs.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from a markdown information form (references/info_form.md) provided by the user. This content is then interpolated into LaTeX templates for the research foundation and working conditions sections.\n- [DATA_EXFILTRATION]: The SKILL.md instructions include a process to report bugs to the vendor's GitHub repository (huangwb8/bensz-bugs) using the gh command-line tool. This operation is conditional and only occurs when explicitly requested by the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 01:46 AM