code-debug
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection within its research and delegation workflows.
- Ingestion points: File SKILL.md ingests untrusted data via WebSearch and WebFetch tools, and SUBAGENT.md ingests user-provided context (logs, messages, or symptoms).
- Boundary markers: No delimiters or instructions to ignore embedded commands are present when interpolating retrieved data or user context into prompts.
- Capability inventory: SKILL.md (WebSearch, WebFetch) and SUBAGENT.md (Task tool, agent invocation) have capabilities to interact with external web resources and delegate tasks to sub-agents.
- Sanitization: There is no evidence of input validation, escaping, or sanitization of the external content or user context before it is processed.
Audit Metadata