gsd-remove-phase
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
BashandWritetools to perform programmatic edits to roadmap files and execute git commands to record historical changes. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it ingests and processes content from external roadmap files.
- Ingestion points: Roadmap content and state are resolved through file reads during the initialization and execution phases.
- Boundary markers: No explicit markers or delimiters are defined to isolate data ingested from roadmap files from the agent's core instructions.
- Capability inventory: The skill is granted
Read,Write,Bash, andGlobcapabilities, allowing it to modify the file system and execute shell commands based on inputs derived from roadmaps. - Sanitization: The skill does not implement validation or sanitization for the data read from the roadmap files before processing.
Audit Metadata