Citation Tracker
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data in the form of manuscripts and reference lists.
- Ingestion points: The skill collects manuscripts and bibliographic reference lists from users (SKILL.md, Step 1).
- Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially embedded commands within the ingested text.
- Capability inventory: The skill instructs the agent to verify DOIs and URLs, which implies the ability to perform network lookups or tool-based verification (SKILL.md, Step 3).
- Sanitization: There are no instructions provided for sanitizing, escaping, or filtering the content of the manuscript or citations before processing.
Audit Metadata