srt-translator
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is designed to ingest and process untrusted external data in the form of subtitle files (SRT, VTT, TXT).
- Ingestion points: Subtitle content provided by the user within the chat prompt (SKILL.md, 'How to Use' section).
- Boundary markers: Absent. The instructions do not specify the use of delimiters or explicit 'ignore embedded instructions' warnings for the input text.
- Capability inventory: None. The skill does not define subprocess calls, file writes, or network operations. It is limited to text transformation and display.
- Sanitization: Absent. There is no instruction to sanitize or filter the input text for malicious commands.
- Risk Assessment: While an attacker could embed malicious instructions within a subtitle file (e.g., hidden prompt injection), the impact is limited to manipulating the agent's current conversation as the skill lacks any side-effect capabilities.
Audit Metadata