implement-with-validation
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process data from external sources, creating a potential surface for indirect prompt injection.
- Ingestion points: The agent is instructed to read repository instructions, environment configurations, and interact with web content through a local Chrome session as described in
SKILL.md. - Boundary markers: No specific boundary markers or delimiters are defined to separate untrusted external data from the agent's instructions.
- Capability inventory: The agent utilizes the
chrome:control-chromeskill for browser automation and executes shell commands for repository discovery (e.g.,git worktree list --porcelain). - Sanitization: The instructions do not specify any validation or sanitization requirements for the content retrieved from the web or repository files before it is processed by the agent.
Audit Metadata