The Agent Skills Directory

EXTERNAL_DOWNLOADS (MEDIUM): The skill instructions direct the agent to use npx -y @transloadit/mcp-server and npx -y @transloadit/node. This results in the download and execution of code from the npm registry at runtime. Although these are the official tools for the Transloadit service, the 'transloadit' organization is not included in the 'Trusted Organizations' whitelist, making the dependency unverifiable by policy.
COMMAND_EXECUTION (LOW): The skill enables the execution of CLI commands via npx to perform media assemblies. This is the primary intended function of the skill and operates within the context of media processing.
CREDENTIALS_UNSAFE (SAFE): The skill uses environment variables (TRANSLOADIT_KEY, TRANSLOADIT_SECRET) to manage authentication. It correctly uses placeholders like YOUR_AUTH_KEY rather than hardcoding sensitive credentials.
DATA_EXFILTRATION (SAFE): No malicious data exfiltration patterns were detected. Network operations are directed towards Transloadit's infrastructure for legitimate media processing tasks.
PROMPT_INJECTION (SAFE): No instructions attempting to override agent behavior or bypass safety filters were found.

transloadit-media-processing