isr-methods
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided research claims, manuscript details, and design descriptions to provide methodological recommendations. This creates a potential surface for indirect prompt injection if malicious instructions are embedded within a research proposal.
- Ingestion points: User research claims and manuscript details processed by the agent in SKILL.md.
- Boundary markers: The skill instructions do not specify any delimiters or explicit 'ignore' instructions for user-provided data.
- Capability inventory: The skill focuses on research design and does not perform file writes, network requests, or system command execution within its own logic, though it references external statistical toolchains.
- Sanitization: There is no evidence of input validation or sanitization for the user-provided research content.
Audit Metadata