The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the clickup-pp-cli binary using npx -y @mvanhorn/printing-press-library and go install github.com/mvanhorn/printing-press-library/.... These resources are hosted on well-known services (NPM and GitHub) and originate from the skill author's own repositories, representing standard vendor resource acquisition.
[COMMAND_EXECUTION]: The skill's primary function is to execute the clickup-pp-cli binary to perform ClickUp operations. This involves running shell commands with user-supplied arguments and flags like --agent.
[DATA_EXFILTRATION]: The CLI includes a --deliver webhook:<url> feature that allows the agent to POST command output (potentially containing ClickUp task data, user details, or workspace info) to an arbitrary external URL. Additionally, the feedback command can be configured to send local notes to a remote endpoint if the CLICKUP_FEEDBACK_ENDPOINT environment variable is set.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from the ClickUp API (task names, descriptions, comments) and processes it within the agent context.
Ingestion points: Data enters the context via sync, task get, search, and docs commands which read from ClickUp's external API or a local SQLite cache.
Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious content embedded in the retrieved ClickUp data.
Capability inventory: The skill possesses significant capabilities, including file writing (--deliver file:<path>), network transmission (--deliver webhook:<url>), and full ClickUp resource management (create, update, delete operations).
Sanitization: The skill does not mention any sanitization or filtering of the content retrieved from the ClickUp API before displaying it to the agent.

pp-clickup