The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes F# source files which could potentially contain malicious instructions embedded in comments or code to influence agent behavior.
Ingestion points: Reads .fs, .fsi, and .fsx files during linting and formatting operations as described in SKILL.md.
Boundary markers: The skill does not explicitly define delimiters or warnings to isolate code content from its internal instructions.
Capability inventory: The skill executes shell commands (dotnet fantomas, dotnet --version) and can modify local source files, as specified in references/tooling/toolchain.md.
Sanitization: There is no evidence of sanitization or filtering applied to the content of the ingested files before processing.
[COMMAND_EXECUTION]: The skill executes local shell commands to interact with the .NET toolchain.
Evidence: The skill uses dotnet --version for environment detection and dotnet fantomas for linting and formatting (found in SKILL.md and references/tooling/toolchain.md). These are standard development operations consistent with the skill's stated purpose.

codeguard-fsharp