connect-ai-jira
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to ingest external data from a Jira instance, which serves as a potential vector for indirect prompt injection attacks.
- Ingestion points: The skill describes processes for retrieving data from the
Issuestable (specifically theSummaryandDescriptioncolumns), theCommentstable (specifically theBodycolumn), and theAttachmentstable via theDownloadAttachmentstored procedure. - Boundary markers: There are no instructions provided in
SKILL.mdto wrap retrieved Jira content in delimiters or to ignore potential instructions embedded within the data. - Capability inventory: The agent has the ability to perform SQL queries (
INSERT,UPDATE,SELECT) and execute stored procedures (such asChangeIssueStatusandArchiveIssues) which could be misused if influenced by malicious data. - Sanitization: The skill does not prescribe any sanitization, validation, or escaping logic for content retrieved from external Jira fields before it is processed by the agent.
Audit Metadata