SRT Enhancer
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill workflow involves reading untrusted content from 'origin.md' and SRT files. This creates a surface for indirect prompt injection where malicious instructions inside those files could attempt to manipulate the agent's output.
- Ingestion points: Content from 'origin.md' and input SRT files are loaded into the agent's context.
- Boundary markers: Not present; the instructions do not define delimiters to isolate external data from the agent's logic.
- Capability inventory: The skill is restricted to text manipulation and writing an 'enhanced.srt' file. It explicitly prohibits the use of Python scripts or automation, which significantly limits the potential impact of an injection.
- Sanitization: No sanitization is performed on the input data to filter out potential instructions or malicious patterns.
Audit Metadata