jira-write-ticket
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Vulnerability to indirect prompt injection through untrusted data sources.
- Ingestion points: The skill instructs the agent to "Find and scan the necessary code" and use the
jira-read-ticketskill to fetch external information from Jira. - Boundary markers: There are no delimiters or specific instructions (e.g., "treat the following as data only") to prevent the agent from executing instructions found within the scanned code or ticket descriptions.
- Capability inventory: The skill utilizes code scanning capabilities and external API access via the
jira-read-tickettool. - Sanitization: There is no evidence of sanitization or filtering of the content retrieved from external sources before it is processed by the agent.
Audit Metadata