dbs-goal
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists exclusively of markdown instructions and a YAML configuration file. No Python or JavaScript code is included for execution.
- [SAFE]: All instructions are centered on project management, goal auditing, and conversation facilitation. There are no patterns related to command execution, data exfiltration, or credential access.
- [PROMPT_INJECTION]: The skill contains instructional markers like 'IMPORTANT' and 'CRITICAL', but these are used legitimately to guide the AI's goal-auditing logic rather than to bypass safety filters or override system prompts.
- [DATA_EXPOSURE]: The skill instructs the AI to read current context and attachments, which is standard behavior for an agent skill and does not involve accessing sensitive system files or credentials.
Audit Metadata