acl-related-work
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional text for academic paper positioning. No malicious patterns, obfuscation, or unauthorized access attempts were identified.
- [NO_CODE]: No executable code, scripts, or installation commands are present in the skill, which eliminates risks associated with remote code execution or persistence.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze user-provided academic drafts, which constitutes a vulnerability surface for indirect prompt injection. 1. Ingestion points: User-provided paper drafts and citation lists. 2. Boundary markers: None specified in the instructions. 3. Capability inventory: No tools or network operations are explicitly requested by the skill. 4. Sanitization: No input validation or escaping mechanisms are provided. Note that this surface is necessary for the skill's legitimate diagnostic purpose.
Audit Metadata