lov-bp
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts (
init_bp.pyandaudit_bp.py) to manage the business plan workspace and perform structural checks on the content. These scripts are part of the skill package and use standard libraries for file manipulation and regex-based parsing. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data such as repository files, product documentation, and website content to generate the BP narrative. While this provides a surface for indirect prompt injection, the risk is mitigated by the specific productivity context and the use of deterministic scripts for auditing and structural validation rather than raw execution of the ingested data.
- [EXTERNAL_DOWNLOADS]: The skill references an external dependency,
lov-any2deck, for the final generation of PPTX and PDF files. This is a modular dependency within the agent environment and follows the platform's standard for skill composition.
Audit Metadata