jira
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
npx @useclawlink/clito execute various Jira-related commands, including logging in, connecting to services, and running actions. - [EXTERNAL_DOWNLOADS]: Fetches the
@useclawlink/clitool from the NPM registry at runtime usingnpxfor CLI operations. - [INDIRECT_PROMPT_INJECTION]: The skill retrieves data from external Jira instances, which serves as a surface for indirect prompt injection if user-generated content in Jira contains malicious instructions.
- Ingestion points: Actions such as
jira_fetch_bulk_issuesandjira_add_comment(when reading context) ingest external data from Jira into the agent's context. - Boundary markers: No explicit markers are defined in the instructions to isolate untrusted data from the agent's control flow.
- Capability inventory: The skill provides capabilities to read and write to Jira, as well as execute shell commands via the ClawLink CLI.
- Sanitization: No sanitization or data validation processes are described for the data retrieved from Jira.
Audit Metadata