skills/codyswanngt/lisa/jira-verify/Gen Agent Trust Hub

jira-verify

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing untrusted JIRA ticket descriptions.
  • Ingestion points: Untrusted data enters via the 'mcp__atlassian__getJiraIssue' tool.
  • Boundary markers: The prompt lacks specific delimiters or instructions to ignore commands within the ticket data.
  • Capability inventory: The skill is restricted to read-only JIRA tools and text recommendations, with no access to system commands or file writing.
  • Sanitization: No sanitization is performed on the retrieved ticket content.
  • [NO_CODE]: The skill consists entirely of instructions and does not ship with any executable code or scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 01:45 AM