goal-tracker

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local commands through a tracker utility located at /root/clawd/tracker to manage state, log activity, and update financial metrics. It also invokes /root/clawd/goal-tracker/generate-dashboard to create HTML visualizations. These commands are integral to the skill's purpose of goal management.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes external data from JSON files that could potentially contain instructions.
  • Ingestion points: Reads data from data/goals.json and data/daily-log.json (SKILL.md).
  • Boundary markers: Absent; the skill does not specify the use of delimiters or 'ignore' instructions for the data it processes.
  • Capability inventory: The skill has the ability to execute shell commands and write to the local file system (e.g., generating index.html).
  • Sanitization: Absent; there is no documented validation or escaping of the contents within the JSON data files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:46 PM
Security Audit — agent-trust-hub — goal-tracker