create-spec
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by design, as its primary purpose is to capture and restructure external data (conversation history) into task files for other agents.
- Ingestion points:
SKILL.mdStep 1 instructs the agent to "extract all of it" and "review the entire conversation" to gather requirements and technical details. - Boundary markers: The skill does not define or use delimiters to wrap the extracted technical details or provide explicit "ignore embedded instructions" warnings for the coder agents that will eventually read these files.
- Capability inventory: The skill has the capability to write multiple Markdown files to the local file system (
specs/{feature-name}/...) via Step 5. - Sanitization: There is no evidence of sanitization, escaping, or filtering of the content extracted from the conversation;
SKILL.mdexplicitly mandates capturing "ALL technical details."
Audit Metadata