The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code files from the project which could potentially contain malicious instructions in comments or string literals. However, the skill lacks any capabilities to act on such instructions beyond including them in a text report. \n
Ingestion points: Reads project source files including Program.cs, Startup.cs, and various .cs, .ts, and .js files to analyze API contracts and consumer logic. \n
Boundary markers: The skill does not define explicit boundary markers or provide instructions to the agent to disregard embedded commands in the files being analyzed. \n
Capability inventory: The skill is strictly limited to generating a report and explicitly states it does not modify code or perform actions beyond static analysis. It has no network, file-write, or shell execution capabilities. \n
Sanitization: No sanitization or escaping of the content read from files is described before it is processed for the report.

api-breaking-change-detector