baoyu-danger-x-to-markdown
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: HIGHCREDENTIALS_UNSAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [Data Exposure & Exfiltration] (HIGH): A hardcoded Bearer token is present in
scripts/constants.ts. Additionally, the skill reads and writes sensitive session cookies (containingauth_tokenandct0) to system application data paths (~/Library/Application Supportor~/.local/share), which are considered sensitive credential files. - [Indirect Prompt Injection] (LOW): The skill processes untrusted data from X.com, creating an attack surface for indirect prompt injection. 1. Ingestion points:
tweet-to-markdown.ts. 2. Boundary markers: Absent. 3. Capability inventory: Network fetch (http.ts) and filesystem write (cookie-file.ts). 4. Sanitization: Absent. - [Privilege Escalation] (LOW): Instructions in
SKILL.mddirect the agent to execute shell commands likecatandmkdirfor consent and configuration management, which involves low-level command execution capabilities.
Recommendations
- AI detected serious security threats
Audit Metadata