requirements-delivery

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it instructs the agent to process "source packages" that include external, untrusted data such as referenced documents and conversations.
  • Ingestion points: The 'Requirement Sources' section in SKILL.md identifies user goals, requirements in any format, referenced documents, and conversations as primary inputs.
  • Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from following malicious commands embedded within the source requirements.
  • Capability inventory: The orchestrator and implementation agents are tasked with executing goals and delivering artifacts based on these requirements, which typically involves file system or environment modifications.
  • Sanitization: There are no explicit requirements for the sanitization, validation, or escaping of ingested requirement data before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 11:35 AM
Security Audit — agent-trust-hub — requirements-delivery