learning-curriculum
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local shell scripts (
scan-repo.shandscaffold-curriculum.sh) to inventory the repository structure and generate curriculum stubs. These scripts are part of the skill's package and perform standard file system operations without network access or privilege escalation. - [INDIRECT_PROMPT_INJECTION]: The skill has an inherent attack surface for indirect prompt injection because it is designed to read and analyze untrusted codebase content (entry points, handlers, and tests) to generate its output.
- Ingestion points: The skill reads various source files (e.g.,
main.go,main.ts, handlers, services, and tests) as part of its 'Step 2: Ground in Executable Sources' logic. - Boundary markers: The instructions do not define specific delimiters or warnings for the agent to ignore embedded instructions within the code being scanned.
- Capability inventory: The skill can execute local scripts and write markdown files to the local file system.
- Sanitization: No explicit sanitization or filtering of the source code content is performed before processing.
Audit Metadata