devils-advocate
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied topics to generate counterarguments, which represents a standard indirect prompt injection surface.
- Ingestion points: The target of the analysis is extracted from the user's most recent message in SKILL.md.
- Boundary markers: No explicit delimiters or isolation instructions are provided for the user input to distinguish it from the skill's operational instructions.
- Capability inventory: The skill's capabilities are limited to spawning a subagent for text generation; it has no access to sensitive system tools, file-system writes, or network operations.
- Sanitization: The skill does not perform sanitization or validation of the input text.
Audit Metadata