context7
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
curlto fetch content from the external domainhttps://context7.com. This domain is used to search for library identifiers and retrieve documentation snippets. - [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands, specifically
curlandjq, to query the API and parse JSON results. The commands are parameterized with library names and search queries. - [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection by ingesting data from an external source into the agent's context.
- Ingestion points: Documentation content is retrieved from
https://context7.com/api/v2/context(SKILL.md). - Boundary markers: No specific delimiters or instructions to ignore embedded commands within the retrieved documentation are provided.
- Capability inventory: The skill is authorized to perform network requests (
curl) and process data (jq). - Sanitization: There is no evidence of filtering or sanitization applied to the retrieved documentation content before it is presented to the agent.
Audit Metadata