disciplined-specification
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Analysis of the skill instructions revealed no malicious patterns, obfuscation, or unauthorized operations. The skill correctly references other components in the author's development suite, such as disciplined-design and disciplined-implementation, representing standard vendor workflow.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its requirement to read and process potentially untrusted project files.
- Ingestion points: Primary specification files (SPEC.md), design documents, and referenced source code files as defined in the 'Input Processing' section.
- Boundary markers: No explicit delimiters or boundary markers are instructed for the agent to use when reading these files.
- Capability inventory: The skill uses AskUserQuestionTool to interact with users and performs file-append operations to update design documents.
- Sanitization: No specific sanitization or filtering logic is provided for the content read from external project files.
Audit Metadata