x-api
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the X API (tweet content, search results), which could contain malicious instructions designed to influence agent behavior.
- Ingestion points: External data enters through API responses in the 'Search Tweets' and 'Read User Timeline' sections of the SKILL.md file.
- Boundary markers: No explicit delimiters or instructions are used in the provided code snippets to isolate or ignore embedded commands within the fetched tweet data.
- Capability inventory: The skill has permissions for network operations (POST/GET) via requests and reading local files for media uploads.
- Sanitization: The skill does not demonstrate any sanitization or filtering of the text content fetched from X before it is processed by the agent.
Audit Metadata