The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill downloads the @pachca/cli package from the npm registry, a well-known service, to facilitate communication with the Pachca platform.
[COMMAND_EXECUTION]: The agent is instructed to execute shell commands using npx and the @pachca/cli tool to retrieve profile information and update account settings.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests and processes data from external API responses.
Ingestion points: Data returned from Pachca API calls such as profile get and custom-properties list (SKILL.md).
Boundary markers: No specific delimiters or instructions to ignore embedded commands in the API output are mentioned in the instructions.
Capability inventory: Shell command execution via npx and the pachca CLI tool (SKILL.md).
Sanitization: No explicit sanitization or validation of the data retrieved from the API is described before the agent processes the output.

pachca-profile