adk-docs
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's operations are confined to the user's local workspace, focusing on searching for ADK code patterns and existing documentation files. All tools (Glob, Grep) and packages (@botpress/runtime) are appropriate for the skill's stated purpose and author identity.
- [PROMPT_INJECTION]: The skill processes untrusted local files, creating a potential surface for indirect prompt injection.
- Ingestion points: The skill reads various project files, including agent.config.ts and documentation in the docs and guides directories (SKILL.md).
- Boundary markers: No specific boundary markers or ignore instructions are provided when reading and processing the contents of these files.
- Capability inventory: The skill is capable of creating and modifying documentation files within the workspace (SKILL.md).
- Sanitization: No sanitization or validation logic is present to identify or neutralize instructions hidden within the ingested text data.
Audit Metadata