Skills
skills/brycewang-stanford/awesome-agent-skills-for-empirical-research/write-well/Gen Agent Trust Hub

write-well

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of markdown-based instructions for the AI. It does not include any scripts, executables, or package manifests.\n- [SAFE]: No network activity, external downloads, or credential-accessing patterns were identified in the instructions.\n- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection (Category 8) because it processes untrusted document content and has file-writing capabilities.\n
  • Ingestion points: The skill reads Quarto (.qmd) files via the Read tool as part of its primary workflow.\n
  • Boundary markers: The instructions do not define delimiters or specific 'ignore' rules to prevent the agent from following instructions potentially embedded within the target document.\n
  • Capability inventory: The skill uses Read and Write file system tools to analyze files and generate reports.\n
  • Sanitization: There is no evidence of sanitization or filtering of the document content before it is processed by the AI.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 10:10 AM
Security Audit — agent-trust-hub — write-well