plan-from-spec

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its ingestion of external specification data.
  • Ingestion points: Untrusted user input is received through the args parameter and used to define the implementation requirements.
  • Boundary markers: The skill lacks explicit delimiters or instructions to the agent to disregard commands embedded within the provided specification text.
  • Capability inventory: The agent has permissions to read various project files (code, documentation, configuration, and infrastructure) and write structured plan documents to the plans/ directory.
  • Sanitization: No validation or sanitization of the input text is performed before it is processed by the agent to determine relevant context and required changes.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 11:08 PM
Security Audit — agent-trust-hub — plan-from-spec