read-x-post
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes untrusted content from X/Twitter posts, which could potentially contain malicious instructions intended for the agent.
- Ingestion points: Data is fetched from api.fxtwitter.com and publish.twitter.com in scripts/read_x_post.py.
- Boundary markers: The skill does not employ specific delimiters or instructions to treat the fetched post text as untrusted data within the agent's context.
- Capability inventory: The script scripts/read_x_post.py performs network read operations using urllib.request.urlopen but does not exhibit file-writing or system command execution based on the fetched content.
- Sanitization: The implementation uses html.unescape for oEmbed content but otherwise provides the raw text as returned by the providers.
- [DATA_EXFILTRATION]: The skill performs network operations to external domains api.fxtwitter.com and publish.twitter.com to fetch post data. While these are necessary for the skill's primary purpose, the domain api.fxtwitter.com is a third-party service and is not on the standard whitelisted domains for data safety.
Audit Metadata