100x-exaggerate
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted script text (source_script) to generate exaggeration and contrast design beats. \n
- Ingestion points: The source_script property in the input JSON, which receives raw TikTok script text from users. \n
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the skill's processing logic. \n
- Capability inventory: The skill performs text analysis and categorization; the associated validation script reads local JSON files and performs string comparisons. No network or shell capabilities are exposed to the ingested data. \n
- Sanitization: The skill does not implement input filtering or escaping for the processed script content.\n- [EXTERNAL_DOWNLOADS]: The skill includes a local validation tool that depends on external software. \n
- The scripts/validate.js tool uses the ajv library for structural JSON Schema enforcement. \n
- The package.json file directs users to install this dependency from the official NPM registry via npm install.
Audit Metadata