github-daily-brief
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it fetches untrusted repository descriptions and metadata from GitHub to generate summaries. Ingestion points: Scraped content from GitHub Trending and Search pages via agent-browser. Boundary markers: Absent; there are no specific instructions or delimiters used to ensure the agent ignores malicious commands embedded in the scraped repository data. Capability inventory: Includes file system writing (Markdown/HTML) and the use of the md-to-pdf skill for document conversion. Sanitization: No sanitization or validation of the fetched external text is specified before it is processed by the LLM.
- [EXTERNAL_DOWNLOADS]: The skill fetches repository information from GitHub's official trending and search URLs, which are well-known and trusted technology services.
Audit Metadata