debugging-wizard
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, potentially untrusted data including error messages, stack traces, and application logs. This creates a vulnerability surface where an attacker could embed malicious instructions within these data sources to influence the agent's troubleshooting flow or command execution.
- Ingestion points: The skill specifically triggers on and processes error messages, stack traces, and log entries provided during debugging sessions.
- Boundary markers: The instructions lack explicit boundary markers or warnings to the agent to treat embedded data as untrusted.
- Capability inventory: The skill leverages powerful shell-based capabilities including language debuggers (pdb, Node.js inspector, Delve) and Git operations (
git bisect). - Sanitization: There are no documented procedures for sanitizing, escaping, or validating the content of the logs or error messages before they are processed by the agent.
Audit Metadata