dotnet-workload
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external 'catalog entries' and 'evidence' to drive its implementation tasks, creating an attack surface for indirect prompt injection.
- Ingestion points: The agent reads requested catalog entries and evidence from external files or input to confirm source revision and implementation status (
SKILL.md). - Boundary markers: The instructions do not define explicit delimiters or warnings to ignore embedded instructions within the catalog data.
- Capability inventory: The agent is instructed to write documentation files (
reliability/properties/<slug>.md) and execute test runner commands based on the catalog mapping. - Sanitization: No specific steps are mentioned for sanitizing or validating the content of the catalog entries before they are translated into code or execution paths.
Audit Metadata