tella-auto-layouts
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from video transcripts and storyboard metadata to determine automated layout decisions, which could allow embedded instructions in the transcript to influence the agent.
- Ingestion points:
get_transcriptandget_storyboard(SKILL.md, workflow step 2). - Boundary markers: Absent. The instructions lack explicit delimiters or "ignore embedded instructions" warnings for the ingested transcript data.
- Capability inventory:
apply_video_edits,update_layout,add_layout,remove_layout, andapply_saved_layout(SKILL.md, workflow step 4). - Sanitization: Absent. There is no evidence of filtering or escaping logic applied to the transcript content before it is used for decision logic.
- [PROMPT_INJECTION]: The skill instructions explicitly direct the agent to skip user confirmation, increasing autonomy and reducing oversight.
- Evidence: "Auto layouts is a direct action: apply the layouts, then report what you did. Don't ask for approval first; the user can undo or ask for changes." (SKILL.md, Scope section).
Audit Metadata