common-observability
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and instrument untrusted source code across multiple languages, creating a vulnerability surface where malicious instructions embedded in those files could influence agent behavior.
- Ingestion points: The skill triggers on a wide variety of backend files including
.ts,.go,.java,.kt, and.pyfiles as defined inSKILL.md. - Boundary markers: There are no instructions for the agent to use delimiters or isolation techniques (like wrapping file content in XML tags) when processing these external files.
- Capability inventory: The agent is instructed to perform complex modifications to service logic, middleware, and interceptors.
- Sanitization: No validation or sanitization steps are defined for the code being ingested and processed.
Audit Metadata