zoe-reviewing-discovered-tasks

Pass

Audited by Gen Agent Trust Hub on May 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it requires the agent to read and evaluate discovery reports which may contain untrusted data.
  • Ingestion points: The agent ingests data from the output of probe discover report (SKILL.md).
  • Boundary markers: The instructions lack delimiters or specific warnings to ignore instructions that might be hidden within the discovery reports.
  • Capability inventory: The skill can execute task management actions and update project scopes via the probe command suite, including probe message directive.
  • Sanitization: There are no instructions for the agent to sanitize or validate the content of the discovery reports before taking action based on them.
Audit Metadata
Risk Level
SAFE
Analyzed
May 6, 2026, 06:19 PM