The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from ClickUp tasks and comments, creating a surface for indirect prompt injection attacks.
Ingestion points: protocols/read-task.md reads task data via clickup task and clickup comments commands.
Boundary markers: Absent. The agent is not instructed to treat task content as potentially malicious or untrusted data.
Capability inventory: The skill has access to the Bash tool (allowing system command execution) and Write (for file creation).
Sanitization: No sanitization or filtering is performed on external task content before it is processed by the agent.
[REMOTE_CODE_EXECUTION]: The protocols/setup.md file contains instructions to download and execute a shell script.
Evidence: The agent is instructed to run git clone https://github.com/TechTechWizard/claude-work-tools.git followed by ./install.sh.
Note: This action is performed from the vendor's own repository and requires explicit user consent before proceeding.
[EXTERNAL_DOWNLOADS]: Downloads the CLI toolset from github.com/TechTechWizard/claude-work-tools if not already present on the system.
[COMMAND_EXECUTION]: Uses the Bash tool to interact with the local filesystem and the clickup CLI tool to perform task operations.

clickup