propagate-design-change
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: In Phase 3, the skill constructs a Bash command using a file path provided as a user argument. If the filename is not properly sanitized, this could potentially allow for shell command injection.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes the content of GDD and ADR files, creating an attack surface where malicious instructions embedded in those documents could influence the agent's behavior.
- Ingestion points: Content is ingested from GDD and ADR files in Phases 2, 4, and 5.
- Boundary markers: No explicit boundary markers are used when processing the data from these files.
- Capability inventory: The skill is authorized to use Write and Bash tools, allowing for file modification and command execution.
- Sanitization: The skill does not perform sanitization of the document text before it is processed by the agent.
Audit Metadata