The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from git diff outputs and has the capability to write code to the local filesystem. This presents a surface for indirect prompt injection where malicious content in a PR diff could attempt to influence the agent's instrumentation logic or code modifications.
Ingestion points: Git diff output (Phase 1).
Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions when processing the diff content.
Capability inventory: File writing and code modification (Phase 5).
Sanitization: Absent. The skill translates its reasoning directly into code changes.
[COMMAND_EXECUTION]: The skill executes git diff to analyze code changes. This is a legitimate and necessary function for the skill's purpose of identifying user-facing changes requiring instrumentation.

instrument-pr