scout
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, untrusted sources which could contain malicious instructions aimed at the agent.
- Ingestion points: External documentation websites, vendor engineering blogs, GitHub issue trackers, and community forums (e.g., Stack Overflow) as defined in the source ladder, as well as local files like
node_modulesand lockfiles. - Boundary markers: None identified; the skill does not use specific delimiters or instructions to ignore embedded commands within the fetched research content.
- Capability inventory: The skill uses web search/fetch capabilities and file system operations, including reading local package data and writing research notes to the
docs/research/directory. - Sanitization: There are no explicit sanitization or filtering steps mentioned for the content retrieved from external sources before it is processed or stored.
Audit Metadata