x-api-dev
Warn
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing
x-pythonvia pip andx-sdkvia npm. These are not official SDKs from X and represent unverifiable third-party dependencies from public registries. This poses a supply chain risk, as these package names could be used for typosquatting or malicious purposes. - [COMMAND_EXECUTION]: The skill provides instructions to execute installation commands (
pip install,npm install) for untrusted or unverified software packages. - [PROMPT_INJECTION]: The skill instructs the agent to fetch and process an external documentation index from
https://docs.x.com/llms.txt, which creates a surface for indirect prompt injection. - Ingestion points: The documentation index file at
https://docs.x.com/llms.txt(SKILL.md). - Boundary markers: Absent; there are no instructions to treat the ingested documentation as untrusted or to ignore embedded commands within the text.
- Capability inventory: The skill possesses capabilities for authenticated network requests (
requests,fetch,curl), package installation (pip,npm), and executing script snippets provided in the documentation. - Sanitization: Absent; the content fetched from the external URL is processed directly without validation, filtering, or escaping.
Audit Metadata