1c-bsl-code-generation
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installation command fetches the skill definition from a public repository on GitHub. Evidence: curl command in metadata.json. This is considered safe as it targets a well-known service for skill distribution.
- [COMMAND_EXECUTION]: The installation process involves executing shell commands to prepare the local environment. Evidence: mkdir command in metadata.json used to create directories.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing user-provided descriptions to query external metadata and code repositories.
- Ingestion points: User requests for 1C code generation, metadata searches, and business entity descriptions in SKILL.md.
- Boundary markers: Absent; the skill does not define specific delimiters to separate user data from instructions in its tool calls.
- Capability inventory: Tool calls to mcp_bsl-platform-context_, mcp_1c-metacode_, read_lints, and 1c-copilot-proxy.check_1c_code.
- Sanitization: None detected; user inputs are passed directly to search and validation tools.
Audit Metadata