huashu-article-edit

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious patterns or safety violations were identified in the skill instructions.
  • [NO_CODE]: The skill consists entirely of instructional markdown and does not include any scripts, executables, or package dependencies.
  • [PROMPT_INJECTION]: Indirect prompt injection surface analysis: 1. Ingestion points: Step 1 reads external article content using a Read tool. 2. Boundary markers: None specified in the instructions. 3. Capability inventory: Read and Save tools are utilized across the workflow steps. 4. Sanitization: No specific sanitization of input text is defined. The risk of the agent following instructions embedded within articles is effectively mitigated by the Step 2 requirement to list all modifications and wait for explicit user confirmation before any edits are performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 09:38 AM