content-creator
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted text files through its analysis scripts (
brand_voice_analyzer.pyandseo_optimizer.py). This creates an ingestion surface where malicious instructions embedded in a user-provided file could potentially influence the agent's following actions during the content revision workflow. - Ingestion points: The scripts
scripts/brand_voice_analyzer.pyandscripts/seo_optimizer.pyread content from files provided as CLI arguments. - Boundary markers: The skill does not implement delimiters or 'ignore instructions' warnings when processing or outputting analyzed content to the agent.
- Capability inventory: The skill utilizes shell execution to run Python scripts that read local file contents.
- Sanitization: The scripts perform regex-based text analysis but do not sanitize the input content before printing results back into the agent's context.
Audit Metadata