skills/evans-sam/skills/triage-issue/Gen Agent Trust Hub

triage-issue

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes data from external, potentially untrusted sources.
  • Ingestion points: External context is fetched from Linear issue details, comments, and Notion documents via MCP tools in the 'Gather external context' phase.
  • Boundary markers: The instructions lack specific boundary markers or 'ignore embedded instructions' warnings when interpolating the fetched external context into the agent's analysis flow.
  • Capability inventory: The skill has the ability to create GitHub issues using the gh CLI tool, write local files, and create/modify content in Linear and Notion via MCP.
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the retrieved external data before it is used by the agent to diagnose problems and plan fixes.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 06:03 PM