ensure-docs
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project source code which represents an external, potentially untrusted data source.
- Ingestion points: The skill reads local source files (
.py,.ts,.js,.go) during Phase 2 (Verification) and Phase 4 (Generation) to analyze symbol documentation and implementation details as defined inreferences/workflow.md. - Boundary markers: While prompt templates in
references/workflow.mduse headers likeSTANDARD:andTASK:, they lack explicit delimiters or instructions to ignore potential commands embedded within the source code being analyzed. - Capability inventory: The skill performs file system writes (generating documentation) and executes shell commands (language detection, grep, and documentation linters like
ruff,eslint, andstaticcheck) as detailed inreferences/workflow.md. - Sanitization: There is no evidence of sanitization, validation, or escaping of the source code content before it is processed by the agent or its subagents.
Audit Metadata