skills/tryshift-sh/skills-store/post/Gen Agent Trust Hub

post

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were identified in the skill files.
  • [CREDENTIALS_UNSAFE]: The skill correctly avoids hardcoding secrets. It utilizes a dedicated secret slot x-oauth defined in agent-secrets.yaml to handle bearer token authentication securely.
  • [DATA_EXFILTRATION]: Network operations are restricted to the official X API (api.x.com) and a local gateway (SHIFT_LOCAL_GATEWAY). These are legitimate targets for the skill's stated purpose of posting and managing tweets.
  • [INDIRECT_PROMPT_INJECTION]: While the skill processes user-supplied text for social media posts, it functions as a controlled output tool. No automated processing of untrusted external data (such as reading and executing instructions from incoming tweets) is implemented, minimizing the risk of indirect injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 11:21 AM