debugger
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data such as code snippets, stack traces, and runtime state logs to perform debugging tasks. This represents a potential surface for indirect prompt injection if the processed data contains malicious instructions intended to influence the agent's behavior.
- Ingestion points: Processes feature paths, components, services, diff areas, stack traces, and runtime state as described in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the external data being analyzed.
- Capability inventory: No dangerous shell commands, network operations, or file-write capabilities were found in the skill content. The metadata explicitly specifies a
sandbox_mode: read-onlyrestriction. - Sanitization: There is no evidence of automated sanitization, escaping, or validation of the ingested debugging data before processing.
Audit Metadata