grey-haven-onboarding-coordination
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The
SKILL.mdfile grants the agent access to theBashtool. While used for automation and environment setup, providing a shell to an agent increases the risk that it could be used to execute unintended or malicious commands if the agent's context is compromised. - [PROMPT_INJECTION] (LOW): The skill has a high surface for Indirect Prompt Injection (Category 8).
- Ingestion points: Data is ingested from the Linear project management tool (
mcp__linear__*) and from various local files viaRead,Glob, andGreptools. - Boundary markers: None are present in the documentation or template indices to instruct the agent to ignore instructions embedded within the onboarding data or issue descriptions.
- Capability inventory: The agent possesses a dangerous combination of tools, including file writing (
Write,TodoWrite), command execution (Bash), and external API interaction (Linear). - Sanitization: There is no evidence of sanitization or validation of the data retrieved from external sources before it is used in coordination or script execution tasks.
Audit Metadata