the-jira-cloud-platform-rest-api
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documentation enables the agent to retrieve and process content from external sources which may contain malicious instructions. The agent also possesses the capabilities to modify sensitive Jira configurations based on its understanding of the documentation. \n
- Ingestion points: The agent is instructed to retrieve data from Jira through operations like
bulkFetchIssues(inreferences/operations/bulkFetchIssues.md) andIssue search(inreferences/operations/findUsers.md). \n - Boundary markers: There are no markers or instructions provided to the agent to distinguish system-provided documentation from data retrieved from the API, nor any guidance to ignore instructions embedded in the data. \n
- Capability inventory: The skill details powerful administrative operations including managing user groups (
references/operations/addUserToGroup.md), configuring workflows (references/operations/createWorkflow.md), and performing bulk issue operations (references/operations/bulkDeleteWorklogs.md). \n - Sanitization: The documentation does not specify any sanitization, validation, or filtering requirements for the data retrieved from Jira before it is processed or acted upon by the agent.
Audit Metadata