marketing-ab-testing
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from external context files, which could potentially contain malicious instructions if those files are controlled by an attacker.
- Ingestion points: The agent is instructed to read from
.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.mdbefore proceeding with the task. - Boundary markers: None identified; the instructions do not specify the use of delimiters or provide warnings to ignore embedded instructions within the ingested content.
- Capability inventory: No risky capabilities (such as subprocess execution, file system writes, or network exfiltration) are defined within the skill's scripts or instructions.
- Sanitization: There is no mention of sanitizing or validating the content retrieved from the external files before the agent processes it.
Audit Metadata