stream-chain
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines workflows that ingest untrusted data from external sources, creating a surface for indirect prompt injection.
- Ingestion points: Data extracted from external API responses, CSV file processing, and analysis of codebase contents including Git change logs.
- Boundary markers: The documentation does not specify the use of delimiters or 'ignore' instructions to isolate ingested data from the agent's operational instructions.
- Capability inventory: The skill is designed to perform file system writes (applying refactoring, generating unit tests) and execute sequential command chains via the 'claude-flow' CLI.
- Sanitization: There is no evidence of sanitization, escaping, or validation of external data before it is interpolated into the workflow's prompt chain.
Audit Metadata