dotnet-mcaf-devex
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from the repository's setup and configuration files to drive its automation workflow. \n
- Ingestion points: The skill analyzes the current local setup, build/run/debug/test commands, and onboarding friction points as documented in SKILL.md. \n
- Capability inventory: The skill instructions involve executing build, run, debug, and test commands based on the analyzed repository content. \n
- Boundary markers: While the skill suggests reading AGENTS.md for constraints, it lacks explicit delimiters or instructions to ignore potentially malicious embedded instructions within the project's own files. \n
- Sanitization: There is no evidence of sanitization, validation, or escaping of the repository's configuration or setup commands before they are processed by the agent.
Audit Metadata