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
argsparameter 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