seo-content-writer
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [Prompt Injection] (SAFE): No override, bypass, or instruction-extraction patterns were found in the skill files.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network exfiltration patterns were identified.
- [Obfuscation] (SAFE): No encoded content, zero-width characters, or homoglyphs are present. The guidelines for avoiding AI-detected phrases are stylistic and not used to conceal malicious intent.
- [Indirect Prompt Injection] (LOW): The skill processes user-provided topics for content generation (Ingestion: User input). No explicit boundary delimiters are used to wrap this input (Boundary: Absent). The skill references local scripts for functionality (Capability: Python script execution) but does not detail sanitization (Sanitization: Absent). The risk is low as the output is display-oriented.
- [No Code] (INFO): The skill references multiple utility scripts (scripts/generate_metrics.py, etc.) that were not provided for analysis, preventing a full audit of the executable components.
Audit Metadata