stream-chain
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's architecture for multi-agent coordination involves streaming outputs from one task to the next, creating a vulnerability surface where malicious instructions in initial data can influence subsequent automated steps.
- Ingestion points: The skill is designed to process external API responses, CSV files, and raw codebase content during analysis, transformation, and refactoring tasks (SKILL.md).
- Boundary markers: The provided examples and instructions lack delimiters or explicit warnings for the agent to ignore instructions embedded within the data it processes.
- Capability inventory: The skill facilitates codebase modification, code generation, and the persistence of execution context in
.claude-flow/memory/(SKILL.md). - Sanitization: There is no evidence of input validation, filtering, or escaping mechanisms to prevent external content from being interpreted as instructions by the LLM during the chaining process.
Audit Metadata