resolve-linear-tech-debt

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill uses official Linear MCP tools (mcp__linear-server) to read and update issues. These interactions are consistent with the skill's documented purpose and target a well-known service.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes external issue data from Linear.
  • Ingestion points: Issue titles and descriptions are fetched using the mcp__linear-server__list_issues tool in SKILL.md.
  • Boundary markers: The fetched data is interpolated into a sub-agent prompt for the 'Explore' agent (e.g., Research tech debt item: "[debt title]"). While the title is wrapped in quotes, there are no specific instructions to ignore embedded commands.
  • Capability inventory: The skill can execute codebase exploration, update issue states, and post comments to Linear.
  • Sanitization: There is no evidence of string sanitization or validation of the fetched Linear data before it is passed to the sub-agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 11:18 PM
Security Audit — agent-trust-hub — resolve-linear-tech-debt