grafana-docs

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by instructing the agent to fetch and process external documentation content from the Grafana Labs domain based on user queries.
  • Ingestion points: External documentation pages from the grafana.com/docs tree, as well as curated machine-readable files like llms.txt and llms-full.txt (SKILL.md, Workflow Step 1 and 2).
  • Boundary markers: The instructions do not specify the use of delimiters or explicit warnings to the agent to disregard instructions found within the retrieved documentation text.
  • Capability inventory: The skill facilitates the retrieval and interpretation of external web content, which could be used to influence agent behavior if the source content is manipulated.
  • Sanitization: The skill does not provide instructions for filtering or sanitizing content retrieved from the external documentation pages before it is summarized for the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 11:52 AM
Security Audit — agent-trust-hub — grafana-docs