research
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 data from external, potentially untrusted sources which could contain instructions aimed at manipulating the agent's behavior.
- Ingestion points: Data enters the agent context through
web_fetch_md(external web pages),gh(GitHub content), and existing repository research notes. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the retrieved data.
- Capability inventory: The skill has the ability to execute network operations via
ghandweb_fetch_md, and it can perform file-write operations to save research notes. - Sanitization: There are no documented steps for sanitizing, escaping, or validating the external content before it is processed by the agent.
Audit Metadata