context7
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The Python script
scripts/context7.pyperforms network requests tohttps://context7.com/api/v2. This external communication is required for the skill's primary function but constitutes a data channel to a non-whitelisted domain. - [INDIRECT_PROMPT_INJECTION]: The skill processes documentation fetched from an external source (
context7.com). This creates a vulnerability surface where malicious instructions embedded in the documentation could attempt to influence the agent's behavior. - Ingestion points: Documentation text is fetched and printed to stdout in
scripts/context7.py(viafetch_docsandsearch_libraryfunctions), which the agent then reads. - Boundary markers: There are no explicit delimiters or instructions for the agent to ignore embedded commands within the fetched documentation content.
- Capability inventory: The skill's capabilities are restricted via the
allowed-toolsfrontmatter to only running thecontext7.pyscript, which mitigates the risk of an injection gaining broad system access. - Sanitization: No filtering or sanitization is performed on the text returned from the API before it is presented to the agent.
Audit Metadata