recipe-task

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user input ($ARGUMENTS) by interpolating it directly into instructions for a sub-agent (rule-advisor) without sanitization or boundary markers.
  • Ingestion points: User input enters via the $ARGUMENTS variable in SKILL.md.
  • Boundary markers: Absent. The user input is placed directly inside a prompt string for the sub-agent: "Analyze the task and select appropriate rules for: $ARGUMENTS...".
  • Capability inventory: The skill has the capability to spawn agents (spawn_agent) and execute implementation steps based on the potentially influenced output of the sub-agent.
  • Sanitization: No evidence of input validation, escaping, or explicit instruction delimiters to prevent the agent from obeying instructions embedded within the task description.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 10:14 PM
Security Audit — agent-trust-hub — recipe-task