wrike
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on
npx @useclawlink/clito facilitate communication between the agent and Wrike. These shell commands are used for logging in, authorizing the connection, and executing specific actions within the Wrike environment. The credentials for this service are stored locally at~/.clawlink/credentials.json. - [INDIRECT_PROMPT_INJECTION]: Because this skill enables the agent to read data from an external productivity tool (Wrike), it creates a surface for indirect prompt injection if Wrike tasks or descriptions contain malicious prompts designed to manipulate the agent.
- Ingestion points: Data fetched from the Wrike API via the
npx @useclawlink/cli run wrikeandactionscommands. - Boundary markers: The instructions include a guideline to "confirm with the user before any write," which provides a manual checkpoint, though it does not explicitly use technical delimiters for the ingested data.
- Capability inventory: The skill allows the agent to execute CLI commands and perform read/write operations on project data.
- Sanitization: There is no evidence of automated sanitization, filtering, or escaping of the content retrieved from Wrike before it is processed by the agent.
Audit Metadata