context7
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: Performs outbound network requests to
context7.comusingcurlto search for and retrieve documentation. While functional for the skill's purpose, this involves sending user-supplied parameters to a non-whitelisted external domain. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external content from a third-party API and provides it to the agent, creating a surface where malicious instructions in the documentation could influence agent behavior.
- Ingestion points: API responses from
https://context7.com/api/v2/contextas documented inSKILL.md. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the fetched documentation as untrusted data.
- Capability inventory: The skill utilizes
curlandjqfor network and data operations. - Sanitization: There is no evidence of filtering or validation performed on the documentation content before it enters the agent's context.
Audit Metadata