lcs-onboarding
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill scans untrusted repository files (READMEs, configuration files, etc.) to generate its reports.
- Ingestion points: Step 1 of the Behavior Checklist scans the entire repository for configuration and documentation files.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded instructions within the scanned files.
- Capability inventory: The skill has the capability to write files to the
.lcs/work-items/directory and update the.lcs/state.mdfile. - Sanitization: There is no evidence of sanitization or filtering of the content extracted from the repository files before it is interpolated into the output templates.
- [DATA_EXFILTRATION]: The skill instructs the agent to 'Extract primary environment variables or configuration options' and include them in the
onboarding.mdreport. - Evidence: The Output Template for
onboarding.mdincludes a table for Environment Variables with 'Description' and 'Default / Example' columns. If the agent extracts actual values from local configuration files, sensitive secrets could be exposed in the markdown documentation.
Audit Metadata