content-creator
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides Python scripts that ingest and analyze user-supplied text files (e.g., blog drafts, existing content). This creates a vulnerability surface for indirect prompt injection, as malicious instructions embedded within the content being analyzed could potentially influence the agent when it processes the analysis results.
- Ingestion points:
scripts/brand_voice_analyzer.pyandscripts/seo_optimizer.pyread content from local files provided as command-line arguments (e.g.,existing_content.txt,blog_post.md). - Boundary markers: The instructions do not define clear delimiters or include specific warnings for the agent to ignore any natural language instructions that might be contained within the content processed by the scripts.
- Capability inventory: The skill includes local file reading and text processing capabilities via regular expressions and frequency analysis across its Python scripts.
- Sanitization: The analysis scripts do not perform sanitization or filtering of the input text before processing and outputting the analysis data to the agent's context.
Audit Metadata