tutorial-context-pack
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external YAML and JSONL files to generate tutorial context packs, which creates a surface for indirect prompt injection.
- Ingestion points: The
scripts/run.pyscript reads data fromoutline/module_plan.ymlandoutline/source_coverage.jsonl(or paths provided via CLI arguments). - Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the processed data.
- Capability inventory: The skill possesses file system read and write capabilities, and its output is intended as "writer-ready" input for subsequent agent tasks.
- Sanitization: No sanitization or validation of the content within the input files is performed before it is aggregated and written to the output pack.
Audit Metadata