gs-how
Pass
Audited by Gen Agent Trust Hub on Nov 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it reads and processes external data from the user's codebase.
- Ingestion points: Files within the analyzed repository, accessed via search and read tools in
SKILL.mdandreferences/explorer-prompt.md. - Boundary markers: None identified. The instructions do not use delimiters or explicit "ignore" warnings when processing source code content.
- Capability inventory: The skill is explicitly scoped to "read-only subagents" in
SKILL.md. Its primary capabilities are file reading and searching; it does not request network access or write permissions during the analysis flow. - Sanitization: None identified.
- [COMMAND_EXECUTION]: The
README.mdfile contains setup instructions usingnpx skills add. These are standard installation commands for the platform and are intended for manual execution by the user, not for the agent to run autonomously.
Audit Metadata