jira
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection vulnerability surface identified.
- Ingestion points: The skill ingests untrusted data from Jira issue summaries, descriptions, and comments through commands like
jira issue viewandjira issue list. - Boundary markers: No specific delimiters or instructions are provided to the agent to treat issue content as untrusted data.
- Capability inventory: The skill allows for writing operations like
jira issue create,jira issue edit, andjira issue comment add, which could be abused if the agent follows malicious instructions found in issue content. - Sanitization: There is no evidence of sanitization or filtering of the incoming Jira data.
Audit Metadata