analytics

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes external data from GitHub environments.
  • Ingestion points: Data is ingested from GitHub pull requests, issues, and commit messages via the mcp_github_github_search_pull_requests and mcp_github_github_search_issues tools as defined in SKILL.md.
  • Boundary markers: The skill lacks explicit instructions or delimiters to isolate untrusted data from the core instructions during processing.
  • Capability inventory: The skill is capable of reading local configuration files such as preferences.md and writing dual-format (Markdown and HTML) reports to the local filesystem at .github/reviews/analytics/.
  • Sanitization: There is no mention of sanitizing or escaping the content retrieved from GitHub before it is included in the generated analytics documents or used for trend narration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 05:34 AM
Security Audit — agent-trust-hub — analytics