rpi-research
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions define a standard workflow for analyzing code and generating documentation. It uses local filesystem access to write research notes in a structured format.
- [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection due to its core function of processing codebase content.
- Ingestion points: Reads local files from the repository during the research phase (Workflow steps 1 and 2).
- Boundary markers: Absent. No specific delimiters or instructions are provided to the agent to ignore potentially malicious content within the researched files.
- Capability inventory: Spawns sub-agents/tasks and writes research memos to the filesystem (rpi/research/).
- Sanitization: Content from the codebase is processed and synthesized without explicit sanitization or validation.
Audit Metadata