twitter-research

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill uses the author's own domain (catalog.selat.ai) for all API requests, which is consistent with the vendor identity (SELAT-AI).\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface because it ingests untrusted data from Twitter/X content.\n
  • Ingestion points: All GET steps defined in manifest.json (fetching user info, tweets, mentions, search results, trends, and replies).\n
  • Boundary markers: Absent; the skill does not explicitly provide delimiters or instructions to ignore embedded commands in the retrieved data.\n
  • Capability inventory: The skill manifest only enables HTTP GET operations to the vendor's API; it does not define any shell execution, file system access, or network exfiltration capabilities.\n
  • Sanitization: The skill does not document any sanitization, validation, or filtering of the external data before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 07:34 PM
Security Audit — agent-trust-hub — twitter-research