skills/gpttang/skill-atlas/crosspost/Gen Agent Trust Hub

crosspost

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill provides example code for sending content to external social media management APIs like postbridge.io. This involves network operations that transmit user data to non-whitelisted third-party services.
  • [PROMPT_INJECTION]: A vulnerability surface for indirect prompt injection exists because the skill processes untrusted user data for distribution without adequate safeguards.
  • Ingestion points: Untrusted content is ingested and adapted in the distribution workflow (SKILL.md).
  • Boundary markers: The instructions do not define clear delimiters or include warnings to ignore instructions embedded in the user content.
  • Capability inventory: The skill outlines capabilities for network requests and potential interaction with other API-based skills (e.g., x-api).
  • Sanitization: There is no documentation or implementation of input sanitization or validation for the content being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 11:09 AM
Security Audit — agent-trust-hub — crosspost