ov-resources

Pass

Audited by Gen Agent Trust Hub on Nov 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and process data from external resources, such as documents, repositories, and URLs, stored under the viking:// URI scheme. This creates a surface for indirect prompt injection attacks.
  • Ingestion points: External content is loaded into the agent's context via tools like read, find, and grep applied to resources in viking://resources/ (SKILL.md).
  • Boundary markers: The instructions do not define any specific delimiters or instructions to help the agent differentiate its core instructions from the content of the documents it reads, increasing the risk of the agent obeying instructions embedded within the data.
  • Capability inventory: The agent can search, list, read, and add resources. While these are retrieval-focused, the agent's interpretation of retrieved data could lead to biased outputs or influence subsequent tool calls.
  • Sanitization: There are no instructions for the agent to sanitize, filter, or ignore potentially malicious content found within the retrieved documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 2, 2026, 11:49 PM