skills/thelobbi/claude/task-details/Gen Agent Trust Hub

task-details

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external content from Jira issue descriptions, which creates a surface for indirect prompt injection.\n
  • Ingestion points: Untrusted data enters the context via the Jira issue description field as part of the enrichment process documented in SKILL.md.\n
  • Boundary markers: The instructions do not define specific delimiters or instructions to prevent the agent from being influenced by commands embedded within the external ticket data.\n
  • Capability inventory: The skill utilizes the mcp.atlassian.updateIssue and mcp.atlassian.searchIssues tools to read and modify Jira data.\n
  • Sanitization: No explicit validation, filtering, or sanitization of the retrieved Jira issue content is implemented in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 10:14 AM
Security Audit — agent-trust-hub — task-details