skills/dcoon/agent-kit/context7/Gen Agent Trust Hub

context7

Pass

Audited by Gen Agent Trust Hub on Nov 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from untrusted external sources, such as documentation websites and public source code repositories, creating a vulnerability to indirect prompt injection.
  • Ingestion points: The outputs of the query-docs and query-code tools in SKILL.md.
  • Boundary markers: None identified. The instructions do not specify the use of delimiters or 'ignore' warnings for the external content.
  • Capability inventory: The skill utilizes resolve-library-id, query-docs, and query-code (which includes grep, definition, and read functions) to interact with external data.
  • Sanitization: No sanitization or validation mechanisms are mentioned for the data retrieved from external repositories or documentation sites.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 17, 2026, 02:04 PM