The Agent Skills Directory

[COMMAND_EXECUTION]: The skill performs shell command execution to interact with the Elixir/Phoenix project environment.
Evidence: Uses grep to locate the ApiSpec module within the lib/ directory.
Evidence: Executes mix openapi.spec.json and mix openapi.spec.yaml to generate documentation files.
Evidence: Uses git diff to compare generated specifications against existing versions.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the data it processes.
Ingestion points: Reads application source code (.ex files), search results from grep, and the output of mix build tasks and git diff in SKILL.md.
Boundary markers: No delimiters or explicit instructions are provided to the agent to distinguish between its instructions and the content of the files or command outputs being processed.
Capability inventory: The skill can execute shell commands (grep, mix, git) and write to the local filesystem via the generated specification files.
Sanitization: No sanitization or validation is performed on the ingested code or command output before it is incorporated into the agent's context.

openapi