blitzreels-motion-graphics
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [Data Exposure & Exfiltration] (LOW): The skill initiates outbound network connections to 'www.blitzreels.com'. While this is the legitimate service endpoint, it is not on the predefined whitelist of trusted domains. However, no access to sensitive local files (e.g., SSH keys, AWS credentials) was observed.\n- [Indirect Prompt Injection] (LOW): The skill exhibits an attack surface for indirect prompt injection through its handling of API responses. \n
- Ingestion points: External data enters the agent context via curl responses in 'scripts/blitzreels.sh'.\n
- Boundary markers: Absent; the skill does not use delimiters or instructions to ignore embedded commands in the API output.\n
- Capability inventory: The skill has the ability to execute shell commands and perform further network requests.\n
- Sanitization: Absent; output from the API is passed directly to the agent without filtering.\n- [Command Execution] (SAFE): The skill uses local bash scripts ('scripts/playground.sh') to orchestrate API calls. Input parameters are handled with double-quoting, which mitigates simple shell injection risks.
Audit Metadata