shower
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill enables the ingestion and processing of untrusted 'artifact' data by transferring it to a new sub-session, which exposes the agent to indirect prompt injection risks.
- Ingestion points: Artifact contents are passed directly into the context of a new sub-session as described in Step 2 of the workflow.
- Boundary markers: The instructions do not define specific delimiters (e.g., XML tags or triple backticks) or include 'ignore' instructions to prevent the sub-session from executing commands embedded within the artifact content.
- Capability inventory: The skill utilizes the agent platform's capability to spawn subagents or tasks to perform the review.
- Sanitization: There is no mention of filtering, escaping, or validating the artifact's content before it is handed off to the sub-session.
Audit Metadata