context7
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install or execute the
ctx7package from the public npm registry usingnpm install -g ctx7@latestornpx ctx7@latestto perform documentation lookups. - [INDIRECT_PROMPT_INJECTION]: The skill processes external technical documentation and code examples retrieved at runtime, which represents a potential attack surface for indirect prompt injection.
- Ingestion points: Documentation and code snippets are ingested through the output of the
ctx7 docscommand (SKILL.md). - Boundary markers: The instructions do not specify any delimiters or explicit boundary markers to separate retrieved external content from the agent's internal reasoning.
- Capability inventory: The skill uses the
ctx7CLI for lookups but does not possess high-risk capabilities such as file-system writes, arbitrary shell execution, or persistent network operations based on the content of the retrieved data. - Sanitization: No explicit sanitization, validation, or filtering of the retrieved documentation content is mentioned or implemented in the instructions.
Audit Metadata