vibeflow-reverse-spec
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts (
scripts/map-codebase.pyandscripts/map-change-impact.py) using the system's python interpreter. These commands use the{project_root}variable as an argument to target the current codebase. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it is designed to ingest and summarize untrusted project source code into documentation. This could allow maliciously crafted code comments or structures to influence the generated architectural context.
- Ingestion points: Ingests Python (.py) and TypeScript/JavaScript (.ts, .tsx, .js, .jsx) source files from the project directory.
- Boundary markers: No specific delimiters or markers are defined in the skill to separate code content from instructions during processing.
- Capability inventory: The skill can execute shell commands (running the mapping scripts) and write to the local file system (creating
docs/overview/files). - Sanitization: There is no evidence of sanitization or filtering of the source code content before it is processed by the documentation scripts.
Audit Metadata