citation-graph-ingest

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process third-party document corpora, such as law, academic papers, and patents, which creates an attack surface where malicious instructions could be embedded in the processed data.
  • Ingestion points: External document content is retrieved using gbrain search and gbrain get in SKILL.md (Pipeline steps 1 and 2).
  • Boundary markers: The skill explicitly references untrusted-content conventions and instructs the agent to treat citation text as DATA, specifically warning that imperatives embedded in a document must not decide the edge type.
  • Capability inventory: The skill uses gbrain link to write typed edges to the native links table and gbrain graph-query to traverse the graph.
  • Sanitization: The skill relies on model judgment and explicit instructions to disregard embedded imperatives within the corpus, focusing only on the actual citation context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 06:18 PM
Security Audit — agent-trust-hub — citation-graph-ingest