alterlab-rma-citation-manager
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is focused on academic citation management and ethics with no malicious patterns identified.
- [DATA_EXFILTRATION]: No unauthorized network communication or sensitive data access patterns were detected. Web searching is used solely for retrieving citation style updates.
- [COMMAND_EXECUTION]: The skill does not invoke dangerous shell commands or attempt privilege escalation; its capabilities are restricted to document formatting and file writing.
- [PROMPT_INJECTION]: No attempts to override safety filters or bypass core agent constraints were found. The skill has a potential indirect prompt injection surface as it reads external project files (Ingestion points: project drafts and reference lists in SKILL.md; Boundary markers: absent; Capability inventory: web search and file-writing deliverables in SKILL.md; Sanitization: absent), but the risk is assessed as safe given the specific academic scope.
Audit Metadata