yutori-competitor-watch
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, which creates a surface for indirect prompt injection.
- Ingestion points: External content enters the agent context through the
$ARGUMENTSplaceholder (competitor name) inSKILL.mdand via web fetching tools targeting competitor blogs, press releases, and documentation sites. - Boundary markers: The instructions for setting up the scout query do not include specific delimiters or instructions to ignore embedded commands within the fetched external content.
- Capability inventory: The skill interacts with monitoring tools (
create_scout,get_scout_updates,edit_scout) and performs network operations via web fetching. - Sanitization: The instructions do not specify any validation, filtering, or escaping mechanisms for the data retrieved from external sources before it is processed by the agent.
Audit Metadata