skills/lobbi-docs/claude/task-details/Gen Agent Trust Hub

task-details

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted data from Jira issue descriptions, creating an indirect prompt injection surface where malicious ticket content could attempt to influence the agent's requirements extraction or Jira updates.
  • Ingestion points: The skill reads issue descriptions via mcp.atlassian.getIssue.
  • Boundary markers: The skill does not define explicit delimiters or instructions to treat the processed issue description as untrusted data.
  • Capability inventory: The skill possesses write capabilities through the mcp.atlassian.updateIssue tool, allowing it to modify Jira issues based on processed content.
  • Sanitization: No input validation, filtering, or sanitization of the external text is described in the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 07:27 PM