create-specification
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external input to create new files on the system, which is a known attack surface for persisting malicious prompts.
- Ingestion points: User input enters the skill via the
${input:SpecPurpose}variable in theSKILL.mdfile. - Boundary markers: The skill does not employ boundary markers, delimiters, or specific instructions to the AI to ignore instructions potentially embedded within the user-provided purpose.
- Capability inventory: The skill has the capability to write markdown files to the
/spec/directory on the local filesystem. - Sanitization: There is no evidence of validation, sanitization, or escaping of the user input before it is used to generate the final documentation content.
Audit Metadata