The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze external data such as pipeline configurations, pull request metadata, and job run logs. This role creates an attack surface for indirect prompt injection, where an attacker could embed malicious instructions in log outputs or repository content to influence the agent's behavior. The skill includes specific reference sections (provider-behavior.md) that guide the agent to use secure practices like quoting shell expansions and validating artifact producers to mitigate these risks.

ci-cd