easysdd-onboarding
Pass
Audited by Gen Agent Trust Hub on Apr 19, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard filesystem capabilities to initialize the 'easysdd' directory structure and deploy two local Python utility scripts. These scripts, 'search-yaml.py' and 'validate-yaml.py', are designed to search and validate documentation metadata within the local environment and do not involve network activity.
- [PROMPT_INJECTION]: The skill's migration pathway requires reading all markdown files within the repository to generate an audit and migration report. This ingestion of untrusted data represents an indirect prompt injection surface where malicious content in repository files could attempt to influence agent behavior. This is mitigated by the skill's instruction to obtain explicit user confirmation for every file-system operation.
- Ingestion points: Scans all '.md' files in the repository (SKILL.md).
- Boundary markers: None present.
- Capability inventory: File creation, moving, and execution of local Python scripts (SKILL.md).
- Sanitization: Strictly requires user confirmation for all migration mapping and file actions (SKILL.md).
- [DATA_EXFILTRATION]: The skill performs repository-wide scans for markdown documentation. The gathered information is used solely for project organization and is not transmitted outside the local environment.
Audit Metadata