cite-style-converter

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements citation conversion and validation logic (APA, MLA, IEEE, Harvard) using standard string manipulation and regular expressions. All processing occurs locally.
  • [DATA_EXPOSURE]: The script scripts/citation_formatter.py supports reading from a user-provided file path via the --input flag. However, the script does not contain any hardcoded sensitive paths, credentials, or network exfiltration capabilities, maintaining a local-only scope.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted bibliographic data which constitutes an attack surface for indirect prompt injection.
  • Ingestion points: Text data is ingested through standard input, file reading (Path.read_text), or CLI arguments in scripts/citation_formatter.py.
  • Boundary markers: The script does not utilize boundary markers or explicit safety instructions when outputting parsed citation content.
  • Capability inventory: The script's capabilities are restricted to local text processing and standard output. It does not utilize subprocess, os.system, eval, or network libraries.
  • Sanitization: The script performs structural validation through regex to ensure citation integrity but does not filter content for natural language instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 08:59 AM