target-authoring
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to guide the agent in processing and modifying untrusted MSBuild project files, which creates an indirect prompt injection surface.
- Ingestion points: The agent ingests external MSBuild files (
.csproj,.targets,.props) from the repository as described in theSKILL.mdusage guidelines. - Boundary markers: Absent. The skill provides no specific instructions or delimiters to isolate content from these external files to prevent the agent from potentially following embedded instructions.
- Capability inventory:
SKILL.mdincludes templates for MSBuildExectasks and instructions for modifying core project item groups (Compile,FileWrites), which can result in shell command execution and filesystem modifications during the build process. - Sanitization: Absent. There are no directives for the agent to sanitize, escape, or validate the content of the project files before acting on them.
Audit Metadata