paw-ps-product-package-assembler
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill focuses on internal project file management and organization within the .pawbytes workspace directory.
- [SAFE]: All identified tasks, such as generating manifests and audit trails, are standard software engineering practices for deliverable packaging.
- [SAFE]: No network activity or sensitive data access patterns were found; the skill relies entirely on local project data.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external manifest files and product context to drive the packaging logic.
- Ingestion points: Manifest files (e.g., discovery-manifest.json, executor-manifest.json) and product context files.
- Boundary markers: No explicit delimiters are used for data processed from these sources.
- Capability inventory: The skill uses file read/write and directory creation capabilities to organize the product package.
- Sanitization: The skill does not explicitly describe sanitization or validation of the input fields beyond schema extraction.
Audit Metadata