skills/openshift-hyperfleet/hyperfleet-claude-plugins/JIRA Story Point Estimator/Gen Agent Trust Hub
JIRA Story Point Estimator
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
jiraCLI commands (view,list,edit) to interact with JIRA projects. While these are necessary for the skill's primary function, they provide the underlying capability for the agent to modify external data based on analyzed content. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to how it handles external data.
- Ingestion points: Untrusted data enters the agent context via
jira issue view TICKET-KEYas described inSKILL.mdwhen fetching ticket descriptions and acceptance criteria. - Boundary markers: The instructions do not define any delimiters or explicit 'ignore embedded instructions' warnings when the agent processes the fetched JIRA content.
- Capability inventory: The skill has the capability to modify JIRA tickets via
jira issue edit, which could be abused if the agent follows malicious instructions found within a ticket description. - Sanitization: There is no evidence of sanitization, filtering, or validation performed on the JIRA ticket content before it is processed by the language model.
Audit Metadata