time-tracking
Fail
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION] (HIGH): Automated scans detected a dangerous pattern where content from 'https://www.rescuetime.com/anapi/focustime' is used in a subprocess execution. This allows a remote attacker controlling the API response to execute arbitrary commands on the host machine.
- [EXTERNAL_DOWNLOADS] (MEDIUM): The skill downloads data from untrusted external sources (Toggl and RescueTime APIs) without performing integrity or safety checks. While these are legitimate services, the execution of downloaded content constitutes a significant risk.
- [PROMPT_INJECTION] (LOW): The skill is vulnerable to indirect prompt injection because it processes untrusted data from external APIs that could contain malicious instructions.
- Ingestion points: API JSON responses retrieved from Toggl and RescueTime.
- Boundary markers: None identified; the skill does not use delimiters to isolate external data from instructions.
- Capability inventory: Network access via 'requests' and 'curl' for GET, POST, and PATCH operations.
- Sanitization: No sanitization or validation of external input is implemented in the provided code snippets.
Recommendations
- HIGH: Downloads and executes remote code from: https://www.rescuetime.com/anapi/focustime - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata