从音频文件中提取文字(语音转文字),需要腾讯云 API 凭据。当用户提到音频转文字、语音识别、ASR、音频转字幕时使用。
72
87%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
The skill examples and parameter list require embedding appid/secret_id/secret_key as literal function arguments, which forces the LLM or generated code to include secret values verbatim (high exfiltration risk).
2b1996b
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.