jira
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
npx @useclawlink/clicommand to perform authentication and Jira operations. This involves executing code in the local shell environment. It also references the sensitive file path~/.clawlink/credentials.jsonwhere authentication tokens are stored.\n- [EXTERNAL_DOWNLOADS]: The skill fetches the@useclawlink/clipackage from the public npm registry at runtime usingnpx. This is a standard distribution method for the toolset provided by the vendor.\n- [PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection by interpolating user-provided text into CLI arguments.\n - Ingestion points: User-supplied task descriptions and JSON input fields.\n
- Boundary markers: Commands use double and single quotes to delimit user input.\n
- Capability inventory: The agent has the ability to execute shell commands and interact with external APIs via the CLI.\n
- Sanitization: The skill relies on the agent's default handling of shell arguments and does not provide explicit sanitization instructions.
Audit Metadata