dotnet-reliability-research
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze untrusted external data, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: The agent is directed to read source code, project files (e.g.,
global.json, NuGet/Paket dependencies), and incident reports to build its reliability model (SKILL.md, lines 20, 29, 36). - Boundary markers: The instructions do not specify the use of delimiters or clear separation markers when the agent processes the contents of these files.
- Capability inventory: The skill utilizes file system read capabilities to perform its research and file system write capabilities to generate documentation output in the
reliability/research/directory (SKILL.md, line 58). - Sanitization: No explicit instructions are provided for sanitizing or validating the contents of the ingested files before they are processed or included in documentation outputs.
Audit Metadata