skills/odyssey4me/agent-skills/jira/Gen Agent Trust Hub

jira

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from Jira issues and comments, creating a potential surface for indirect prompt injection.\n
  • Ingestion points: Untrusted data such as issue summaries, descriptions, and comments are retrieved via the Jira REST API in scripts/jira.py.\n
  • Boundary markers: The script does not utilize specific delimiters or instructions to the model to ignore potentially malicious instructions embedded within the Jira content.\n
  • Capability inventory: The skill includes tools to create issues, update fields, add comments, and transition workflows through scripts/jira.py, which could be exploited if an injection is successful.\n
  • Sanitization: No explicit sanitization or filtering is performed on the text content retrieved from Jira before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 04:11 AM