workflow-spec-to-pbi
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface because it ingests and processes untrusted documentation to drive the generation of backlog items and UI mockups.\n
- Ingestion points: The workflow reads from specification files located in docs/specs/.\n
- Boundary markers: The skill lacks explicit delimiters or instructions for the model to ignore potentially malicious embedded content within the source documentation.\n
- Capability inventory: The workflow includes operations to create and modify project files, generate stories, and prioritize tasks across multiple internal tools.\n
- Sanitization: No sanitization or validation of the input documentation content is specified before it is used to generate output artifacts.
Audit Metadata