research
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute specific GitHub CLI commands (
gh api) and standard Git operations (git clone). These are restricted to the primary purpose of retrieving repository data for research. - [EXTERNAL_DOWNLOADS]: Fetches content from external web URLs and GitHub repositories via
WebFetch,tavily_extract_process, andgit cloneto provide source-based answers (SKILL.md, references/repo-cloning-pattern.md). - [PROMPT_INJECTION]: Identified an indirect prompt injection surface where the agent processes untrusted external content.
- Ingestion points: External data enters the context via
WebFetch,tavily_extract_process,gh api, andgit clone(SKILL.md, references/repo-cloning-pattern.md). - Boundary markers: Absent. No specific delimiters or "ignore embedded instructions" warnings are defined for the fetched content.
- Capability inventory: The skill can execute
Bash,Task,Read, andGrepoperations (SKILL.md). - Sanitization: Absent. The skill does not explicitly sanitize or filter the retrieved content before it is read or summarized by the agent.
Audit Metadata