content-creator
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates text analysis using included Python scripts (
brand_voice_analyzer.pyandseo_optimizer.py) and utilizes standard shell commands (grep,cp) for template management and content verification. These actions are confined to the local environment and are necessary for the skill's function.\n- [INDIRECT_PROMPT_INJECTION]: The skill's analysis tools process external text content. 1. Ingestion points: The scripts read file contents passed as command-line arguments. 2. Boundary markers: Absent. 3. Capability inventory: The scripts are limited to printing textual analysis results to the console and do not have access to the network or file-writing tools. 4. Sanitization: Absent. The potential for indirect prompt injection is mitigated by the extremely limited capability set of the analysis scripts.
Audit Metadata