gjalla-spec
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands via the
gjallaCLI, includinggjalla spec newfor file scaffolding and other subcommands to retrieve system architecture. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to the ingestion of external project metadata and code.
- Ingestion points: Data retrieved via
gjallaCLI (architecture, capabilities, rules) and local source code (SKILL.md). - Boundary markers: No specific boundary markers or 'ignore' instructions are present to mitigate embedded instructions.
- Capability inventory: The skill has the ability to execute CLI tools and write to the filesystem.
- Sanitization: No validation or sanitization of the retrieved architecture specifications or source code is performed before the agent processes them.
Audit Metadata