The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by processing untrusted data from the repository.
Ingestion points: External files and documentation are read in Step 2 and Step 4b (e.g., README files, inline docs, perf logs).
Boundary markers: No specific delimiters or instructions to ignore embedded commands within the read data are provided.
Capability inventory: The skill utilizes the Bash and Read tools to interact with the environment.
Sanitization: There is an absence of explicit sanitization or validation logic for the content retrieved from external files before it is processed by the agent.
[COMMAND_EXECUTION]: The skill explicitly directs the agent to perform shell command execution through the Bash tool to calculate file metrics, such as using wc -c to determine byte and character counts.

impact-measurement