code-architecture-writer
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use git utilities (
git diff,git log,git rev-parse) to perform repository analysis and identify changes between branches.\n- [DATA_EXFILTRATION]: The agent reads local project files using standard file-reading tools to extract code snippets and analyze logic for the generated documentation.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes external codebase content.\n - Ingestion points: Files are read via the
Readtool in Phase 2, andgit logoutput is consumed in Phase 1 as described in SKILL.md.\n - Boundary markers: Absent; there are no specific instructions to use delimiters or to ignore embedded instructions within the analyzed code comments.\n
- Capability inventory: The skill uses
gitcommands and fileRead/Edit(write) tools to perform its tasks, as outlined in the workflow in SKILL.md.\n - Sanitization: No content sanitization or filtering is specified for the ingested code before it is processed by the AI.
Audit Metadata