redlines
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes the
@houfu/redlinesJavaScript library for document transformation. This dependency is scoped to the skill's author and is consistent with the skill's stated purpose.\n- [COMMAND_EXECUTION]: The skill performs local file system operations by reading original Word documents and writing modified DOCX files with tracked changes.\n- [SAFE]: The documentation includes proactive security and privacy advice, explicitly warning that author metadata is persisted in Word XML and recommending metadata-scrubbing steps before external document delivery.\n- [SAFE]: Comprehensive accountability and escalation procedures are established, including confidence bands that trigger human review for complex document structures.\n- [PROMPT_INJECTION]: The skill processes untrusted text input to generate document revisions. \n - Ingestion points: Untrusted data enters via the
modifiedTextparameter in theapplyRedlinesfunction (SKILL.md).\n - Boundary markers: None; the tool is designed as a mechanical transform for upstream diffs.\n
- Capability inventory: File system write access via the
toDocxmethod (SKILL.md).\n - Sanitization: No specific sanitization of external text is mentioned, as the skill provides a direct mapping from text input to document revisions.
Audit Metadata