content-atomizer
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process "seed content" (blog posts, transcripts, etc.) provided by the user. This creates a surface for indirect prompt injection where malicious instructions embedded in the source text could attempt to override the agent's behavior.
- Ingestion points: Seed content provided by the user in the "Intake" section of
SKILL.md. - Boundary markers: Absent. The instructions do not specify the use of delimiters or specific prompts to ignore instructions within the user-provided text.
- Capability inventory: The skill is limited to text generation and does not include subprocess execution, file system writes, or network operations.
- Sanitization: Absent. There is no logic to sanitize or validate the provided text for malicious injection patterns.
Audit Metadata