rhetorical-analyst
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text for analysis, which creates a surface for indirect prompt injection.
- Ingestion points: Untrusted text such as debate threads or speeches enters the context as defined in SKILL.md.
- Boundary markers: There are no instructions to use delimiters or ignore embedded instructions in the processed text.
- Capability inventory: The skill uses InfraNodus MCP tools for analysis; it lacks capabilities for arbitrary file access or network communication.
- Sanitization: No sanitization or escaping of the user-provided text is prescribed.
Audit Metadata