content-repurposing
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed entirely of natural language instructions and does not contain any executable scripts, shell commands, or external package dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external source assets such as transcripts or drafts which could contain malicious instructions.
- Ingestion points: The "source asset" (link, transcript, or draft) in Step 1.
- Boundary markers: Absent; no specific instructions are provided to the agent to treat the source as data rather than instructions.
- Capability inventory: None; the skill does not request or use any tools for network operations, file system modification, or command execution.
- Sanitization: Absent; the skill assumes the input content is safe for processing.
Audit Metadata