linear-backlog-manager

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its core workflow of parsing and acting upon specification files.
  • Ingestion points: The skill reads input from documentation/specs/{feature}/tasks.md, requirements.md, and design.md as described in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions are defined to protect the agent from embedded commands or malicious instructions within the ingested markdown content.
  • Capability inventory: The skill uses the Linear MCP to create and modify project issues (save_issue), writes a ticket-map.md file to the local filesystem, and updates external documentation pages on platforms like Notion or Confluence.
  • Sanitization: The instructions do not prescribe any validation, filtering, or escaping of the content extracted from the specification files before it is used in API payloads or documentation updates.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 01:24 PM
Security Audit — agent-trust-hub — linear-backlog-manager