academic-paper-reviewer
Pass
Audited by Gen Agent Trust Hub on Nov 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided content (academic papers), which is a common surface for indirect prompt injection attacks.
- Ingestion points: User-provided abstract, full text, and PDF files mentioned in SKILL.md.
- Boundary markers: The instructions do not define explicit delimiters to separate user input from the system's review instructions.
- Capability inventory: No sensitive capabilities such as network access, file system modifications, or arbitrary command execution were detected.
- Sanitization: No input sanitization or validation logic is present.
- [SAFE]: No patterns of prompt injection, data exfiltration, obfuscation, or unauthorized privilege escalation were identified. The skill's behavior is consistent with its stated purpose of academic paper evaluation.
Audit Metadata