technical-spec
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified in the skill's instructions or scripts. The skill follows best practices for a documentation generation tool.
- [COMMAND_EXECUTION]: The skill uses a local Python script (
scripts/check_index.py) for documentation index validation. This script is part of the skill package and only performs safe, read-only checks on local file names and index links using standard library modules. - [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided business documentation as context for generating technical specifications, creating a surface for indirect prompt injection.
- Ingestion points: Content from
docs/business/,CLAUDE.md, andAGENTS.md. - Boundary markers: Absent; the instructions do not define specific delimiters for external content.
- Capability inventory: The skill allows writing to the
docs/technical-specs/directory and executing the providedcheck_index.pyscript. - Sanitization: Absent; there is no explicit sanitization of the input documentation.
- Assessment: The capability set is restricted to documentation management, and the input source (local project documentation) is low-risk in this context.
Audit Metadata