project-governance-bootstrap

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill implements a workflow that requires the agent to ingest data from external platforms including Linear, Notion, and GitHub. This design introduces a surface for indirect prompt injection, where an attacker could place malicious instructions in issue descriptions or documentation to influence the agent's actions during the governance setup or maintenance.\n
  • Ingestion points: Data is ingested from Linear issues/comments, Notion page content, and repository markdown files (e.g., AGENTS.md, ROADMAP.md, and MISSION.md).\n
  • Boundary markers: The skill instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when the agent interpolates external content into its processing loop.\n
  • Capability inventory: The agent has permissions to perform file system writes (creating and modifying documentation), and it uses tools to interact with Linear and Notion APIs for project and memory management.\n
  • Sanitization: There is no requirement in the skill for the agent to sanitize, escape, or validate the content retrieved from external systems before acting upon it.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 09:45 AM
Security Audit — agent-trust-hub — project-governance-bootstrap