The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill recommends installing the Truto CLI by piping a remote shell script from the vendor's domain directly to the shell. Evidence: curl -fsSL https://cli.truto.one/install.sh | bash and irm https://cli.truto.one/install.ps1 | iex in SKILL.md. This is a standard installation method for the vendor's developer tools.
[COMMAND_EXECUTION]: The skill uses several shell commands for CLI-based authentication and operational checks. Evidence: truto login --token "$TRUTO_API_TOKEN" and truto whoami -o json in SKILL.md.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from diverse third-party integrations, creating a surface for indirect prompt injection.
Ingestion points: Integration data is ingested through endpoints such as GET /unified/crm/contacts as described in SKILL.md.
Boundary markers: The reference materials do not explicitly define the use of delimiters or instructions to ignore embedded commands for the data being processed.
Capability inventory: The skill is capable of performing network fetch requests to api.truto.one and writing data back to integrated accounts.
Sanitization: No explicit content sanitization or validation logic is demonstrated for the records retrieved from integrations.

truto