content-creator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- PROMPT_INJECTION (SAFE): The instructions in SKILL.md and reference guides are focused strictly on marketing workflows. No patterns attempting to bypass safety filters or override core agent behavior were identified.
- DATA_EXFILTRATION (SAFE): No hardcoded credentials, API keys, or network-enabled code (such as requests or curl) were found. The tools operate entirely on local text data.
- REMOTE_CODE_EXECUTION (SAFE): The brand_voice_analyzer.py script uses only standard Python libraries (re, typing, json, sys). No mechanisms for downloading or executing remote code are present.
- COMMAND_EXECUTION (SAFE): The skill documentation suggests standard CLI usage of the provided scripts. No suspicious subprocess calls, privilege escalation (sudo), or system-level modifications were detected.
- INDIRECT_PROMPT_INJECTION (SAFE): While the brand_voice_analyzer.py script ingests untrusted content for analysis, it lacks exploitable capabilities. It only performs regex-based text analysis and arithmetic calculations for readability scores, making it resilient to instruction-based data attacks.
Audit Metadata