adk-docs
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code and documentation from the user's workspace, creating an attack surface where malicious instructions embedded in project files could potentially influence agent behavior.
- Ingestion points: The skill is designed to read user project code, configuration files such as
agent.config.ts, and markdown documentation located in./docs/or./guides/(specified inSKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when the agent processes these external files.
- Capability inventory: The skill utilizes workspace tools such as
GlobandGrepfor searching and provides automated commands to create or update documentation files (specified inSKILL.md). - Sanitization: There is no evidence of sanitization, validation, or filtering of content extracted from the project files before it is processed by the agent.
Audit Metadata