improve-codebase-architecture
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to ingest and process data from external codebases which could contain malicious instructions.
- Ingestion points: The skill instructs the agent to explore the mental map of the filesystem and read codebase content (found in
SKILL.md). - Boundary markers: The skill explicitly mandates human oversight ("the human is the strategic programmer", "do not AFK-rewrite"), though it lacks technical delimiters for the data it ingests.
- Capability inventory: The agent has the capability to write refactor RFCs and implement code changes (
SKILL.md). - Sanitization: The skill does not define specific sanitization or filtering procedures for the content read from the codebase.
Audit Metadata