mega-brain-com-copy-thief
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The metadata 'description' field contains instructions in Portuguese designed to override or specifically direct the AI's behavior, using phrases like 'use the total force of mega brain' and 'copy thief that is triggered in the system'.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided video scripts and context (Step 1 and Step 4 in SKILL.md) to generate new content. It lacks clear boundary markers or sanitization, which could allow instructions embedded in that user data to manipulate the AI's output.
- Ingestion points: SKILL.md Workflow Step 1 ('Re-read the user's original context and the older video material') and Step 4 ('connect the new video to the initial context').
- Boundary markers: None identified.
- Capability inventory: The skill performs text analysis and generation; no external tool invocations or filesystem writes are requested.
- Sanitization: None identified.
Audit Metadata