efficient-web-research
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources such as web pages, GitHub repositories, and search snippets.
- Ingestion points: Data enters the agent context through tools like read_url_content, browser_subagent, and the GitHub API as specified in the SKILL.md protocols.
- Boundary markers: The instructions in SKILL.md do not specify the use of delimiters or explicit warnings for the agent to ignore embedded instructions within fetched content.
- Capability inventory: The skill facilitates data extraction, structured reporting, and summarization; it does not request high-risk capabilities like shell execution or file-system modifications.
- Sanitization: The protocol instructs the agent to strip HTML boilerplate (navigation, ads, cookie banners) and summarize content before final output.
- [SAFE]: The skill references and fetches metadata and documentation from the official GitHub API (api.github.com), which is a well-known technology service.
Audit Metadata