skill-my-account
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of local Python scripts, including
account_stats.py,xhs_publish.py,douyin_publish.py, andweb_publisher.py, to perform browser automation and data retrieval. - [DATA_EXFILTRATION]: The skill accesses sensitive session information stored in local browser profiles at
~/.easel-browser-profiles/. This directory contains cookies and authentication tokens necessary for the skill to verify login status and fetch account data. Handling such session data involves inherent security considerations regarding credential exposure. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from social media platforms, creating a vulnerability to indirect prompt injection.
- Ingestion points: Data such as post titles, article content, and user statistics are retrieved from external platform creator centers using Playwright-based scripts.
- Boundary markers: The skill documentation does not define explicit delimiters or instructions for the agent to isolate external data from its own core instructions.
- Capability inventory: The skill can execute local shell commands and perform network operations via automated browser instances.
- Sanitization: No procedures for sanitizing or validating the data retrieved from external social media services are mentioned in the skill instructions.
Audit Metadata