explaining-architecture
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes local codebase implementation files, which creates a potential surface for indirect prompt injection if an attacker includes malicious instructions within code comments or documentation. However, the skill is explicitly read-only and lacks network or shell execution capabilities, which mitigates the risk of exfiltration or system compromise.
- Ingestion points: The skill reads implementation files (code, function definitions) to trace data flows and architecture.
- Boundary markers: The instructions do not explicitly mandate delimiters or warnings to ignore instructions found within the code being analyzed.
- Capability inventory: The skill is strictly read-only; it does not have the capability to write files, make network requests, or execute subprocesses.
- Sanitization: No explicit sanitization of the analyzed content is described.
Audit Metadata