lite-spec
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted input from user ideas and existing codebase content to generate specifications, representing an indirect prompt injection surface. This is a common pattern for documentation agents.
- Ingestion points: User brainstorms, bug reports, and codebase files (SKILL.md).
- Boundary markers: None defined.
- Capability inventory: Read-only codebase access and file writing to temporary directories (SKILL.md).
- Sanitization: None mentioned.
- [COMMAND_EXECUTION]: The skill specifies a file path for its output using shell-style environment variables (
${TMPDIR:-/tmp}). This requires the agent to resolve system-specific paths to save the generated specification artifact.
Audit Metadata