update-specification
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to update specification files based on external requirements and existing code. This creates a surface for indirect prompt injection if the source materials contain malicious instructions.
- Ingestion points: The skill ingests
${file}and external 'requirements' or 'updates to any existing code' in theSKILL.mdinstructions. - Boundary markers: The instructions do not specify boundary markers or instructions for the agent to ignore embedded commands within the ingested data.
- Capability inventory: The skill's primary capability involves writing Markdown files to the
/spec/directory. - Sanitization: There is no requirement for the agent to sanitize or validate the external content before processing it.
Audit Metadata