The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted content from the ClickUp API.\n
Ingestion points: Data including task names, descriptions, and project hierarchies are retrieved from the ClickUp API via endpoints such as /clickup/api/v2/task/{task_id}.\n
Boundary markers: The instructions and examples do not include delimiters or specific guidance to the agent to treat retrieved task content as untrusted data.\n
Capability inventory: The skill allows the agent to execute shell-based Python commands and perform network operations, which could be exploited if an injection is successful.\n
Sanitization: No sanitization or filtering logic is provided for the text content fetched from external sources.\n- [DATA_EXFILTRATION]: Performs network requests to external service domains.\n
Evidence: The skill communicates with gateway.maton.ai, ctrl.maton.ai, and connect.maton.ai.\n
Context: These endpoints are documented as the vendor's managed infrastructure for the integration and are necessary for the skill's purpose.\n- [COMMAND_EXECUTION]: Provides Python code blocks for interaction with the API.\n
Evidence: SKILL.md contains multiple examples using the python <<'EOF' pattern to execute scripts for workspace listing and connection management.

clickup