citation-check

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data (such as PDFs, slides, and web search results) to verify factual claims. This capability introduces a vulnerability surface for indirect prompt injection if the processed content contains hidden instructions meant to influence the agent's behavior.
  • Ingestion points: The skill reads user-provided documents and performs web searches to verify claims (SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters or defensive prompts to isolate the external content from the agent's logical execution environment.
  • Capability inventory: The skill uses file-read operations and network search capabilities to perform its task (SKILL.md).
  • Sanitization: There are no explicit rules for sanitizing or escaping the content retrieved from external sources before it is analyzed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:31 PM
Security Audit — agent-trust-hub — citation-check