ab-testing
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to ingest information from local files to establish marketing context, which serves as a potential vector for indirect instructions.
- Ingestion points: Instructions in
SKILL.mddirect the agent to read from.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.mdbefore proceeding. - Boundary markers: The instructions do not specify any delimiters or safety prompts to prevent the agent from following instructions potentially embedded within these context files.
- Capability inventory: The skill does not contain executable scripts, subprocess calls, network exfiltration commands, or file writing operations.
- Sanitization: There is no logic provided to sanitize or validate the content of the referenced context files.
Audit Metadata