manage-freeze-windows

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it retrieves and processes external configurations (such as freeze window names, descriptions, and YAML) from the Harness platform. This content could potentially contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: Data enters the agent's context through the output of the harness_list and harness_get tools as referenced in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore commands that may be embedded within the retrieved data.
  • Capability inventory: The skill enables the agent to perform state-changing operations using harness_create, harness_update, harness_delete, and harness_execute.
  • Sanitization: There is no explicit requirement or instruction for sanitizing or validating the content of the external data before it is incorporated into the prompt context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 10:16 AM
Security Audit — agent-trust-hub — manage-freeze-windows