linkedin-content
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses local Python scripts (
format_picker.py,post_linter.py, andrepurpose_splitter.py) to perform its primary functions. These scripts are invoked via standard shell commands within the workflow. The scripts use only the Python standard library and perform deterministic text processing tasks. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied content (LinkedIn drafts and source documents) to perform linting and splitting. While these scripts do not use explicit delimiters, their execution environment is highly restricted, limited to regex analysis and writing a local JSON ledger file, which minimizes the risk of successful injection attacks.
- [DATA_EXPOSURE]: The skill uses a local file (
.linkedin-ledger.json) to track content hashes and publication dates to prevent duplicate posting. This is a standard state management practice and does not involve the handling of sensitive credentials or private user data.
Audit Metadata