criar-tasks
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from PRD and Tech Spec files to generate task descriptions.
- Ingestion points: Reads specification data from
tasks/prd-[feature-slug]/prd.mdandtasks/prd-[feature-slug]/techspec.md. - Boundary markers: The skill does not define delimiters or provide 'ignore embedded instructions' warnings when reading these external files.
- Capability inventory: The skill has the capability to read from and write to the local filesystem (creating files in the
tasks/directory). - Sanitization: There is no validation or escaping of the content extracted from the specification documents before it is used to generate the final task files.
Audit Metadata