tella-changelog-video
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, which creates a potential surface for indirect instructions to influence agent behavior.
- Ingestion points: The skill reads user-provided release notes from pasted text, local files, or external links as described in Step 1 of the Plan (SKILL.md).
- Boundary markers: There are no explicit delimiters (e.g., XML tags or triple quotes) or instructions for the agent to ignore embedded commands within the processed notes.
- Capability inventory: The skill uses Tella MCP tools for video manipulation (
duplicate_video), persisting layouts and styles (save_text_preset,save_layout), and configuring multimedia elements (set_background_music) as noted in the Build and Next Time sections of SKILL.md. - Sanitization: No input validation, escaping, or filtering of the content retrieved from the user-provided notes or links is specified.
Audit Metadata