x-api
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes Python scripts via
uv runand shell heredocs to interact with the X/Twitter API endpoints. - [EXTERNAL_DOWNLOADS]: Dynamically installs the
requests-oauthlibpackage from the standard PyPI registry to handle OAuth 1.0a signing. - [PROMPT_INJECTION]: Inherits an indirect prompt injection surface by ingesting and processing untrusted data from Twitter mentions and search queries.
- Ingestion points: Fetches content from
api.twitter.com/2/users/*/mentionsandapi.twitter.com/2/tweets/search/recent. - Boundary markers: The implementation lacks specific delimiters or instructions to treat external data as untrusted.
- Capability inventory: The skill can post tweets, reply to tweets, delete tweets, and follow users.
- Sanitization: No sanitization or filtering logic is provided for the data retrieved from the external API before it is presented to the agent.
Audit Metadata