paper-citation-planner
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for a text-generation task. No malicious patterns, obfuscation, or dangerous system commands were detected.
- [COMMAND_EXECUTION]: No shell commands, system calls, or external scripts are present in the instructions or frontmatter.
- [DATA_EXFILTRATION]: No sensitive data exposure or exfiltration patterns were found. The skill processes academic-related inputs like bibliography keys and paper outlines.
- [PROMPT_INJECTION]: No attempts to bypass safety filters or override agent constraints were detected in the prompt logic.
- [SAFE]: Indirect prompt injection surface analysis: Ingestion points: topic, paper_preferences, outline, source_pack, bibliography in SKILL.md. Boundary markers: Absent. Capability inventory: None. Sanitization: Absent. The risk is negligible as the skill lacks tools or system access capabilities.
Audit Metadata