ai-error-prevention
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates the processing of untrusted user data, such as software specifications and curriculum references, which presents a surface for indirect prompt injection.
- Ingestion points: The workflow in SKILL.md and references/app-specific-prevention.md directs the agent to ingest user-provided requirements and application contexts.
- Boundary markers: No specific delimiters or instruction-blocking markers are prescribed for separating user data from system instructions.
- Capability inventory: The agent is designed to generate and iterate on code, which typically involves file system access and execution within a development environment.
- Sanitization: There are no instructions for sanitizing or validating user input before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill mandates the use of a 'Superpowers plugin' in SKILL.md for all operations. This is an unverifiable dependency as no source URL, versioning information, or integrity checks are provided, making its origin and security posture unknown.
Audit Metadata