tella-plan-video
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided content such as transcripts and scripts which could potentially contain malicious instructions. \n
- Ingestion points: User-provided scripts, outlines, and video transcripts as described in SKILL.md. \n
- Boundary markers: Absent; there are no specific instructions to delimit user content from system instructions. \n
- Capability inventory: The skill utilizes the tella MCP and interacts with related skills like tella-auto-cut and tella-auto-layouts for video processing. \n
- Sanitization: Absent; no validation or escaping of input text is defined.\n- [SAFE]: No malicious patterns, obfuscation, or unauthorized access were detected. The skill uses standard tool access for its designated purpose.
Audit Metadata