test-analyze
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from external files (XML, JSON, HTML) specified in the results path. This creates a surface for indirect prompt injection where malicious content inside a test report could influence agent behavior.
- Ingestion points: The prompt instructs the agent to read and extract data from the path provided in
{{ARG1}}usingRead,Glob, andGreptools. - Boundary markers: The instructions do not define delimiters or provide specific warnings to the model to ignore embedded instructions within the ingested test data.
- Capability inventory: The skill possesses significant capabilities including systematic planning via
mcp__pal__plannerand task delegation to multiple subagents (security-audit, code-refactoring, etc.) via theTasktool. - Sanitization: There is no evidence of content sanitization or validation before the data is passed to the planning model or subagents.
Audit Metadata