clockify-tracker
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECREDENTIALS_UNSAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill implements a priority-based resolution for the
CLOCKIFY_API_KEY. It searches environment variables (CLOCKIFY_API_KEY,CLOCKIFY_API_KEY_FILE), reads from arbitrary file paths provided in variables, and executesgrepcommands against shell configuration files (~/.zshrc,~/.zprofile,~/.bashrc,~/.bash_profile,~/.profile) to extract secrets. While this is for the intended API usage, searching system shell configs for secrets is a sensitive operation. - [COMMAND_EXECUTION]: Executes shell commands to retrieve configuration and read logs, including
grepfor secret extraction andcatto read both the API key file and the preference JSON file (~/.clockify-prefs.json). - [INDIRECT_PROMPT_INJECTION]: The skill features a 'Log-based mode' that reads content from local markdown files in
~/.work-log/YYYY-MM-DD.md. It parses these files to determine projects, repos, and descriptions. This creates a surface where malicious instructions embedded in a work log file could influence the agent's behavior during the 'Log-based mode' workflow.
Audit Metadata