The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl and jq system binaries to interact with the Asana REST API. These operations are restricted to standard API calls and do not perform unauthorized system changes.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes user-controlled data retrieved from an external source.
Ingestion points: The skill retrieves task names, notes, and comments via Get task and List tasks operations from Asana's API.
Boundary markers: No explicit delimiters or instructions are provided to distinguish between retrieved data and agent instructions.
Capability inventory: The skill enables the agent to execute shell commands and modify workspace content.
Sanitization: No sanitization or validation is performed on the data returned from the API before it is processed by the agent.

asana