debugging-wizard
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data such as error messages, log entries, and execution traces. Ingestion points: Processes external data in SKILL.md (Core Workflow) and references/systematic-debugging.md (Phase 1). Boundary markers: Absent. The instructions do not specify the use of delimiters or provide 'ignore' instructions for content found within logs or error messages. Capability inventory: References the use of powerful debugging and inspection tools such as pdb, node --inspect, dlv, and git bisect. Sanitization: Absent. No specific steps are mentioned for sanitizing or filtering the content of the ingested debug data.
- [EXTERNAL_DOWNLOADS]: The reference guide in references/debugging-tools.md suggests the use of the well-known Go package github.com/davecgh/go-spew/spew for inspecting complex data structures.
Audit Metadata