The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and process untrusted repository data while possessing the capability to modify files.
Ingestion points: Uses Read, Glob, and Grep tools to inspect repository workflows, adapters, and source code.
Boundary markers: No specific instructions are provided to the agent to ignore or delimit instructions found within the repository files being analyzed.
Capability inventory: The skill is granted Write and Edit permissions in its allowed-tools to modify CI configurations and repository files.
Sanitization: While the instructions emphasize using "sanitized fixtures," there is no explicit sanitization for the agent's interpretation of code comments or strings as instructions.
[SAFE]: The skill promotes security best practices for CI/CD environments, including the use of offline contract fixtures to avoid live credential usage in untrusted forks and explicit requirements for secret redaction in logs.
[SAFE]: All external documentation links and resource references target official Salesloft developer domains.

salesloft-ci-integration