The Agent Skills Directory

[PROMPT_INJECTION]: The skill interacts with repository data which could serve as a vector for indirect prompt injection.
Ingestion points: The skill reads output from git diff for change detection, ls for directory audits, and grep for file content scanning.
Boundary markers: The final output summary does not use specific delimiters or instructions to isolate potentially untrusted file data from the agent's context.
Capability inventory: The skill utilizes bun, git, ls, and grep through the Bash tool, along with the Read and Grep tools.
Sanitization: No explicit sanitization or filtering of the raw command output is performed before inclusion in the final report.
[COMMAND_EXECUTION]: The skill executes a repository-local script (./scripts/validate-marketplace.ts) using the bun runtime. This is a standard and expected operation for project-specific auditing and CI/CD validation tasks.

validate-plugins