skills/upstash/context7/docs/Gen Agent Trust Hub

docs

Warn

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the 'ctx7' package from the NPM registry using 'npm install -g ctx7@latest'. This package is not associated with the known trusted vendors or the author's specified naming conventions.
  • [REMOTE_CODE_EXECUTION]: The skill utilizes 'npx ctx7@latest' to execute code directly from a remote repository, which is a high-risk pattern for executing unverified scripts.
  • [COMMAND_EXECUTION]: Multiple shell commands are executed to interact with the documentation service, including 'ctx7 library', 'ctx7 docs', and 'ctx7 login'.
  • [CREDENTIALS_UNSAFE]: The skill manages authentication through 'ctx7 login' and instructions to 'export CONTEXT7_API_KEY', which involves handling sensitive credentials within the agent's environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data returned from external documentation queries, creating a surface for indirect prompt injection.
  • Ingestion points: Output from 'ctx7 library' and 'ctx7 docs' commands (SKILL.md).
  • Boundary markers: Absent; the agent is instructed to use the results directly without delimiters.
  • Capability inventory: Shell command execution (ctx7 CLI).
  • Sanitization: Absent; the skill does not specify any validation or escaping for the retrieved documentation content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 09:22 PM