jira
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
jira-clitool via Homebrew, referencing the public repository athttps://github.com/ankitpokhrel/jira-cli. - [COMMAND_EXECUTION]: The skill executes the
jiraCLI tool to perform all operations, including reading and writing data to Atlassian Jira instances. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection vulnerabilities through the processing of untrusted Jira ticket content.
- Ingestion points: Data from Jira ticket summaries, descriptions, and comments is ingested into the agent context through
jira issue listandjira issue viewcommands. - Boundary markers: The skill does not provide clear delimiters or instructions to the agent to treat fetched Jira content as untrusted data.
- Capability inventory: The skill possesses write-access capabilities such as
jira issue create,edit, andmove, which could be potentially misused if an injection occurs. - Sanitization: No sanitization or validation mechanisms are present for data retrieved from external Jira sources.
Audit Metadata