skills/openclaw/skills/jira/Gen Agent Trust Hub

jira

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from Jira (e.g., issue summaries, descriptions, and comments) without explicit boundary markers or sanitization logic.\n
  • Ingestion points: Jira API search and issue detail endpoints defined in SKILL.md.\n
  • Boundary markers: Absent.\n
  • Capability inventory: Python snippets using urllib.request for network operations and Jira issue mutations (create/update/delete).\n
  • Sanitization: Absent.\n- [COMMAND_EXECUTION]: The documentation provides multiple Python snippets intended for execution to interact with the API. These snippets access environment variables (MATON_API_KEY) and perform network requests to gateway.maton.ai and ctrl.maton.ai. While functional, they represent an execution surface for data retrieved from the API gateway.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 10:28 AM