clip-a-talking-head
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources which could potentially contain malicious instructions intended to manipulate the agent's output or behavior.\n
- Ingestion points: Media files and transcripts are fetched from user-provided URLs via
import_mediaand processed usingget_media_contextinSKILL.md.\n - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following commands that might be embedded within the processed transcript text.\n
- Capability inventory: The skill possesses extensive media manipulation capabilities, including
apply_composition,create_render, andsetCaptionStyle, which could be influenced by injected content.\n - Sanitization: No evidence of content sanitization or validation is present before the transcript data is used to drive the composition logic.
Audit Metadata