spec-flow-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, potentially untrusted specifications and plans provided by users. Ingestion points: The skill accepts raw text input for specifications and plans in SKILL.md. Boundary markers: No explicit instructions separate user content from the agent logic. Capability inventory: Uses codebase search tools (grep, glob) for gathering context. Sanitization: No content filtering is performed.
Audit Metadata