gstack-plan
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied feature plans and descriptions to generate architecture and engineering reviews. This input is processed without explicit boundary markers or sanitization guidelines, creating an entry point for instructions embedded in the data.
- Ingestion points: User-provided plans and feature descriptions (SKILL.md).
- Boundary markers: Absent; the instructions do not specify delimiters or 'ignore embedded instructions' warnings for untrusted input.
- Capability inventory: The agent uses shell commands (
git log,ls) and file reading capabilities (SKILL.md). - Sanitization: Absent; no escaping, validation, or filtering of external content is defined.
- [COMMAND_EXECUTION]: The skill uses the
executetool to run discovery commands in the repository root at initialization. - Evidence:
git log --oneline -10andlscommands in SKILL.md.
Audit Metadata